version bump 1.15.0: added 28591 to cpexcel

This commit is contained in:
SheetJS 2021-07-29 17:10:04 -04:00
parent ff3c114453
commit 6d1f7cc2d6
62 changed files with 454 additions and 12982 deletions

3
.github/FUNDING.yml vendored Normal file
View File

@ -0,0 +1,3 @@
github: SheetJSDev
custom: https://sheetjs.com
open_collective: s5s

8
.gitignore vendored Normal file
View File

@ -0,0 +1,8 @@
node_modules
package-lock.json
*.tgz
codepages/
.vocrc
misc/coverage.html
codepage_mini.md
ctest/sauce*

View File

@ -22,6 +22,7 @@ Wansung
halfwidth
# Third-party
ECMA-35
FoxPro
nodejs
unicode.org

View File

@ -3,8 +3,11 @@ LIB=codepage
VOC=voc
TARGET=cptable.js
AUXTARGETS=cputils.js cpexcel.js sbcs.js
DISTFULL=cpexcel sbcs cptable
CMDS=bin/codepage.njs
DISTFULL_A=cpexcel sbcs
DISTFULL_B=cptable
CMDS=
#DISTBITS=iso2022.js
DISTBITS=
ULIB=$(shell echo $(LIB) | tr a-z A-Z)
FLOWTARGET=cptable.js
@ -16,14 +19,16 @@ CLOSURE=/usr/local/lib/node_modules/google-closure-compiler/compiler.jar
all: voc ## Build library and auxiliary scripts
.PHONY: voc
voc test.js: codepage.md
$(VOC) codepage.md
voc: codepage.md
@make js
#$(VOC) codepage.md
.PHONY: js
js: make.sh codepage.md ## Build all output targets
bash make.sh <(awk -F, '$$3=="1"' pages.csv) sbcs.js cptable
bash make.sh excel.csv cpexcel.js cptable
bash make.sh
bash make.sh pages.csv cptable.js cptable
#node iso2022/make_iso2022.njs > iso2022.js
make cputils.js
cputils.js: cputils.flow.js
@ -31,17 +36,18 @@ cputils.js: cputils.flow.js
.PHONY: clean
clean: ## Remove targets and build artifacts
rm -f make.sh .vocrc pages.csv bits/*.js
rm -f bits/*.js
.PHONY: dist
dist: $(TARGET) $(AUXTARGETS) ## Copy files for distribution
cp $(TARGET) $(AUXTARGETS) LICENSE dist/
for i in $(DISTFULL); do cat $$i.js cputils.js | sed "s#require('./cptable')#cptable#" > dist/$$i.full.js; done
for i in $(DISTFULL_A); do cat $$i.js cputils.js | sed "s#require('./cptable')#cptable#" > dist/$$i.full.js; done
for i in $(DISTFULL_B); do cat $$i.js $(DISTBITS) cputils.js | sed "s#require('./cptable')#cptable#" > dist/$$i.full.js; done
## Testing
.PHONY: test mocha
test mocha: test.js $(TARGET) baseline ## Run test suite
test mocha: $(TARGET) baseline ## Run test suite
mocha -R spec -t 20000
.PHONY: ctest
@ -67,7 +73,7 @@ fullint: lint old-lint tslint flow mdlint ## Run all checks
.PHONY: lint
lint: $(TARGET) $(AUXTARGETS) ## Run eslint checks
@eslint --ext .js,.njs,.json,.html,.htm $(TARGET) $(AUXTARGETS) $(CMDS) $(HTMLLINT) package.json bower.json
@eslint --ext .js,.njs,.json,.html,.htm $(TARGET) $(AUXTARGETS) $(CMDS) $(HTMLLINT) package.json
if [ -e $(CLOSURE) ]; then java -jar $(CLOSURE) $(REQS) $(FLOWTARGET) --jscomp_warning=reportUnknownTypes >/dev/null; fi
.PHONY: old-lint

View File

@ -26,7 +26,7 @@ Alternatively, use the full version in the dist folder:
```
The complete set of codepages is large due to some Double Byte Character Set
encodings. A much smaller file that just includes SBCS codepages is provided in
encodings. A much smaller file that only includes SBCS codepages is provided in
this repo (`sbcs.js`), as well as a file for other projects (`cpexcel.js`)
If you know which codepages you need, you can include individual scripts for
@ -133,7 +133,7 @@ to produce a complete script like `cpexcel.full.js`.
## Building the complete script
This script uses [voc](npm.im/voc). The script to build the codepage tables and
the JS source is `codepage.md`, so building is as simple as `voc codepage.md`.
the JS source is `codepage.md`, so building involves `voc codepage.md`.
## Generated Codepages
@ -274,11 +274,11 @@ tables are not generated, there is no corresponding entry (they are "magic").
| `29001` | Windows 7 | Europa 3 |
| `38598` | Windows 7 | ISO 8859-8 Hebrew (ISO-Logical) |
| `47451` | unicode.org | Atari ST/TT |
| `50220` | Windows 7 | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | Windows 7 | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | Windows 7 | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | Windows 7 | ISO 2022 Korean |
| `50227` | Windows 7 | ISO 2022 Simplified Chinese |
| `50220` | magic | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | magic | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | magic | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | magic | ISO 2022 Korean |
| `50227` | magic | ISO 2022 Simplified Chinese |
| `51932` | Windows 7 | EUC Japanese |
| `51936` | Windows 7 | EUC Simplified Chinese |
| `51949` | Windows 7 | EUC Korean |
@ -330,6 +330,9 @@ To update the browser artifacts, run `make ctest`.
- [Windows Code Page Enumeration](http://msdn.microsoft.com/en-us/library/cc195051.aspx)
- [Windows Code Page Identifiers](http://msdn.microsoft.com/en-us/library/windows/desktop/dd317756.aspx)
- [IBM Coded Character Sets](https://www-01.ibm.com/software/globalization/ccsid/ccsid_registered.html)
- [ISO/IEC 2022 / ECMA-35](https://www.ecma-international.org/publications/files/ECMA-ST/Ecma-035.pdf)
- [International Register of Coded Character Sets To Be Used With Escape Sequences](https://www.itscj.ipsj.or.jp/itscj_english/iso-ir/ISO-IR.pdf)
- [Japanese Character Encoding for Internet Messages](https://tools.ietf.org/html/rfc1468)
## License

View File

@ -2,78 +2,14 @@
The fields of the `pages.csv` manifest are `codepage,url,bytes` (SBCS=1, DBCS=2)
```>pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
863,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP863.TXT,1
864,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP864.TXT,1
865,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP865.TXT,1
866,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP866.TXT,1
869,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP869.TXT,1
874,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT,1
875,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT,1
932,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT,2
936,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP936.TXT,2
949,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT,2
950,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT,2
1026,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT,1
1250,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT,1
1251,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT,1
1252,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT,1
1253,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT,1
1254,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT,1
1255,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT,1
1256,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT,1
1257,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT,1
1258,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT,1
47451,http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/ATARIST.TXT,1
```
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private `0xF8FF` code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. Codepages are an absolute pain :/
```>pages.csv
10000,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ROMAN.TXT,1
10006,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/GREEK.TXT,1
10007,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT,1
10029,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT,1
10079,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT,1
10081,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT,1
```
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the `ISO-8859-X` series is `28590 + X`:
```>pages.csv
28591,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT,1
28592,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-2.TXT,1
28593,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-3.TXT,1
28594,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-4.TXT,1
28595,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-5.TXT,1
28596,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-6.TXT,1
28597,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT,1
28598,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-8.TXT,1
28599,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-9.TXT,1
28600,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT,1
28601,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT,1
28603,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT,1
28604,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT,1
28605,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT,1
28606,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT,1
```
## Generated Codepages
The following codepages are available in .NET on Windows:
@ -142,11 +78,6 @@ The following codepages are available in .NET on Windows:
- 21866 Ukrainian (KOI8-U); Cyrillic (KOI8-U)
- 29001 Europa 3
- 38598 ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
- 50220 ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
- 50221 ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS Allow 1 byte Kana)
- 50222 ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS Allow 1 byte Kana - SO/SI)
- 50225 ISO 2022 Korean
- 50227 ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
- 51932 EUC Japanese
- 51936 EUC Simplified Chinese; Chinese Simplified (EUC)
- 51949 EUC Korean
@ -163,107 +94,11 @@ The following codepages are available in .NET on Windows:
- 57010 ISCII Gujarati
- 57011 ISCII Punjabi
```>pages.csv
708,,1
720,,1
808,,1
858,,1
870,,1
872,,1
1010,,1
1047,,1
1132,,1
1140,,1
1141,,1
1142,,1
1143,,1
1144,,1
1145,,1
1146,,1
1147,,1
1148,,1
1149,,1
1361,,2
10001,,2
10002,,2
10003,,2
10004,,1
10005,,1
10008,,2
10010,,1
10017,,1
10021,,1
10082,,1
20000,,2
20001,,2
20002,,2
20003,,2
20004,,2
20005,,2
20105,,1
20106,,1
20107,,1
20108,,1
20261,,2
20269,,1
20273,,1
20277,,1
20278,,1
20280,,1
20284,,1
20285,,1
20290,,1
20297,,1
20420,,1
20423,,1
20424,,1
20833,,1
20838,,1
20866,,1
20871,,1
20880,,1
20905,,1
20924,,1
20932,,2
20936,,2
20949,,2
21025,,1
21027,,1
21866,,1
29001,,1
38598,,1
50220,,2
50221,,2
50222,,2
50225,,2
50227,,2
51932,,2
51936,,2
51949,,2
52936,,2
54936,,2
57002,,2
57003,,2
57004,,2
57005,,2
57006,,2
57007,,2
57008,,2
57009,,2
57010,,2
57011,,2
```
The following codepages are dependencies for Visual FoxPro:
- 620 Mazovia (Polish) MS-DOS
- 895 Kamenický (Czech) MS-DOS
```>pages.csv
620,,1
895,,1
```
## Building Notes
The script `make.sh` (described later) will get these files and massage the data
@ -289,13 +124,7 @@ which implies that code `0xF6` is `String.fromCharCode(0x02C6)` and vice versa.
To build the sources on windows, consult `dotnet/MakeEncoding.cs`.
After saving the standard output to `out`, a simple script processes the result:
```>dotnet.sh
#!/bin/bash
if [ ! -e dotnet/out ]; then exit; fi
<dotnet/out tr -s ' ' '\t' | awk 'NF>2 {if(outfile) close(outfile); outfile="codepages/" $1 ".TBL"} NF==2 {print > outfile}'
```
After saving standard output to `out`, the `dotnet.sh` script processes results.
# Building the script
@ -304,43 +133,9 @@ generates JS code for encoding and decoding:
## Raw Codepages
```>make.njs
#!/usr/bin/env node
var argv = process.argv.slice(1), fs = require('fs');
if(argv.length < 2) {
console.error("usage: make.njs <codepage_index> [variable]");
process.exit(22); /* EINVAL */
}
var cp/*:string*/ = argv[1];
var jsvar/*:string*/ = argv[2] || "cptable";
var x/*:string*/ = fs.readFileSync("codepages/" + cp + ".TBL","utf8");
var maxcp = 0, i = 0, ii = 0;
var y/*:Array<Array<number> >*/ = x.split("\n").map(function(z/*:string*/)/*:Array<number>*/ {
var w/*:Array<string>*/ = z.split("\t");
if(w.length < 2) return [Number(w[0])];
return [Number(w[0]), Number(w[1])];
}).filter(function(z) { return z.length > 1; });
```
The DBCS and SBCS code generation strategies are different. The maximum code is
used to distinguish (max `0xFF` for SBCS).
```
for(i = 0; i != y.length; ++i) if(y[i][0] > maxcp) maxcp = y[i][0];
var enc/*:{[key:string]:number}*/ = {}, dec/*:{[key:string]:string}|Array<string>*/ = (maxcp < 256 ? [] : {});
for(i = 0; i != y.length; ++i) {
/*:: if(Array.isArray(dec)) */ dec[y[i][0]] = String.fromCharCode(y[i][1]);
enc[String.fromCharCode(y[i][1])] = y[i][0];
}
var odec = "", outstr = "";
if(maxcp < 256) {
/*:: if(Array.isArray(dec)) { */
```
The Unicode character `0xFFFD` (REPLACEMENT CHARACTER) is used as a placeholder
for characters that are not specified in the map (for example, `0xF0` is not in
code page 10000).
@ -348,14 +143,6 @@ code page 10000).
For SBCS, the idea is to embed a raw string with the contents of the 256 codes.
The `dec` field is merely a split of the string, and `enc` is an eversion:
```
for(i = 0; i != 256; ++i) if(typeof dec[i] === "undefined") dec[i] = String.fromCharCode(0xFFFD);
odec = JSON.stringify(dec.join(""));
outstr = '(function(){ var d = ' + odec + ', D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();';
/*:: } */
} else {
```
DBCS is similar, except that the space is sliced in chunks of 256 bytes (strings
are only generated for those high-bytes represented in the codepage).
@ -363,27 +150,6 @@ The strategy is to construct an array-of-arrays so that `dd[high][low]` is the
character associated with the code. This array is combined at runtime to yield
the complete decoding object (and the encoding object is an eversion):
```
var dd = [];
/*:: if(!Array.isArray(dec)) { */
for(i in dec) if(dec.hasOwnProperty(i)) {
ii = +i;
if(typeof dd[ii >> 8] === "undefined") dd[ii >> 8] = [];
dd[ii >> 8][ii % 256] = dec[i];
}
/*:: } */
outstr = '(function(){ var d = [], e = {}, D = [], j;\n';
for(var i = 0; i != 256; ++i) if(dd[i]) {
for(var j = 0; j != 256; ++j) if(typeof dd[i][j] === "undefined") dd[i][j] = String.fromCharCode(0xFFFD);
outstr += 'D[' + i + '] = ' + JSON.stringify(dd[i].join("")) + '.split("");\n';
outstr += 'for(j = 0; j != D[' + i + '].length; ++j) if(D[' + i + '][j].charCodeAt(0) !== 0xFFFD) { e[D[' + i + '][j]] = ' + (i*256) + ' + j; d[' + (i*256) + ' + j] = D[' + i + '][j];}\n'
}
outstr += 'return {"enc": e, "dec": d }; })();';
}
process.stdout.write(jsvar + "[" + cp + "] = " + outstr + "\n");
```
`make.sh` generates the tables used by `make.njs`. The raw Unicode TXT files
are columnar: `code unicode #comments`. For example, the last 10 lines of the
text file `ROMAN.TXT` (for CP 10000) are:
@ -404,35 +170,6 @@ text file `ROMAN.TXT` (for CP 10000) are:
In processing the data, the comments (after the `#`) are stripped and undefined
elements (like `0x7F` for CP 10000) are removed.
```>make.sh
#!/bin/bash
INFILE=${1:-pages.csv}
OUTFILE=${2:-cptable.js}
JSVAR=${3:-cptable}
VERSION=$(cat package.json | grep version | tr -dc [0-9.])
mkdir -p codepages bits
rm -f $OUTFILE $OUTFILE.tmp
echo "/* $OUTFILE (C) 2013-present SheetJS -- http://sheetjs.com */" > $OUTFILE.tmp
echo "/*jshint -W100 */" >> $OUTFILE.tmp
echo "var $JSVAR = {version:\"$VERSION\"};" >> $OUTFILE.tmp
if [ -e dotnet.sh ]; then bash dotnet.sh; fi
awk -F, '{print $1, $2, $3}' $INFILE | while read cp url cptype; do
echo $cp $url
if [ ! -e codepages/$cp.TBL ]; then
curl $url | sed 's/#.*//g' | awk 'NF==2' > codepages/$cp.TBL
fi
echo "if(typeof $JSVAR === 'undefined') $JSVAR = {};" > bits/$cp.js.tmp
node make.njs $cp $JSVAR | tee -a bits/$cp.js.tmp >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <bits/$cp.js.tmp >bits/$cp.js
rm -f bits/$cp.js.tmp
done
echo "// eslint-disable-next-line no-undef" >> $OUTFILE.tmp
echo "if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = $JSVAR;" >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <$OUTFILE.tmp >$OUTFILE
rm -f $OUTFILE.tmp
```
## Utilities
The encode and decode functions are kept in a separate script (`cputils.js`).
@ -446,412 +183,8 @@ Both encode and decode deal with data represented as:
The `ofmt` variable controls `encode` output (`str`, `arr` respectively)
while the input format is automatically determined.
# Tests
```>test.js
var fs = require('fs'), assert = require('assert'), vm = require('vm');
var cptable, sbcs;
```
Due to a bug in `Buffer.from` in node `4.0 - 4.4`, a special check is needed:
```>test.js
var Buffer_from = function(){};
if(typeof Buffer !== 'undefined') {
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
}
```
The tests include JS validity tests (requiring or evaluating code):
```>test.js
describe('source', function() {
it('should load node', function() { cptable = require('./'); });
it('should load sbcs', function() { sbcs = require('./sbcs'); });
it('should load excel', function() { excel = require('./cpexcel'); });
it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(x) {
vm.runInThisContext(fs.readFileSync('./bits/' + x));
});
});
});
```
The README tests verify the snippets in the README:
```>test.js
describe('README', function() {
var readme = function() {
var unicode_cp10000_255 = cptable[10000].dec[255]; // ˇ
assert.equal(unicode_cp10000_255, "ˇ");
var cp10000_711 = cptable[10000].enc[String.fromCharCode(711)]; // 255
assert.equal(cp10000_711, 255);
var b1 = [0xbb,0xe3,0xd7,0xdc];
var s1 = b1.map(function(x) { return String.fromCharCode(x); }).join("");
var 汇总 = cptable.utils.decode(936, b1);
var buf = cptable.utils.encode(936, 汇总);
assert.equal(汇总,"汇总");
assert.equal(buf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b1[i], buf[i]);
var b2 = [0xf0,0x9f,0x8d,0xa3];
var sushi= cptable.utils.decode(65001, b2);
var sbuf = cptable.utils.encode(65001, sushi);
assert.equal(sushi,"🍣");
assert.equal(sbuf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b2[i], sbuf[i]);
};
it('should be correct', function() {
cptable.utils.cache.encache();
readme();
cptable.utils.cache.decache();
readme();
});
});
```
The consistency tests make sure that encoding and decoding are pseudo inverses:
```>test.js
describe('consistency', function() {
cptable = require('./');
U = cptable.utils;
var chk = function(cptable, cacheit) { return function(x) {
it('should consistently process CP ' + x, function() {
var cp = cptable[x], D = cp.dec, E = cp.enc;
if(cacheit) cptable.utils.cache.encache();
else cptable.utils.cache.decache();
Object.keys(D).forEach(function(d) {
if(E[D[d]] != d) {
if(typeof E[D[d]] !== "undefined") return;
if(D[d].charCodeAt(0) == 0xFFFD) return;
if(D[E[D[d]]] === D[d]) return;
throw new Error(x + " e.d[" + d + "] = " + E[D[d]] + "; d[" + d + "]=" + D[d] + "; d.e.d[" + d + "] = " + D[E[D[d]]]);
}
});
Object.keys(E).forEach(function(e) {
if(D[E[e]] != e) {
throw new Error(x + " d.e[" + e + "] = " + D[E[e]] + "; e[" + e + "]=" + E[e] + "; e.d.e[" + e + "] = " + E[D[E[e]]]);
}
});
var corpus = ["foobar"];
corpus.forEach(function(w){
assert.equal(U.decode(x,U.encode(x,w)),w);
});
cptable.utils.cache.encache();
});
}; };
describe('cached', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, true));
});
describe('direct', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, false));
});
});
```
The next tests look at possible entry conditions:
```
describe('entry conditions', function() {
it('should fail to load utils if cptable unavailable', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
assert.throws(function() {
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
});
it('should load utils if cptable is available', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
vm.runInContext(fs.readFileSync('cpexcel.js','utf8'),ctx);
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
var chken = function(cp, i) {
var c = function(cp, i, e) {
var str = cptable.utils.encode(cp,i,e);
var arr = cptable.utils.encode(cp,i.split(""),e);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.encode(cp,Buffer_from(i),e);
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
cptable.utils.cache.decache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
};
describe('encode', function() {
it('CP 1252 : sbcs', function() { chken(1252,"foo•bþr"); });
it('CP 708 : sbcs', function() { chken(708,"ت and ث smiley faces");});
it('CP 936 : dbcs', function() { chken(936, "这是中文字符测试");});
});
var chkde = function(cp, i) {
var c = function(cp, i) {
var s;
if(typeof Buffer !== 'undefined' && i instanceof Buffer) s = [].map.call(i, function(s){return String.fromCharCode(s); });
else s=(i.map) ? i.map(function(s){return String.fromCharCode(s); }) : i;
var str = cptable.utils.decode(cp,i);
var arr = cptable.utils.decode(cp,s.join?s.join(""):s);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.decode(cp,Buffer_from(i));
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
cptable.utils.cache.decache();
c(cp,i);
};
describe('decode', function() {
it('CP 1252 : sbcs', function() { chkde(1252,[0x66, 0x6f, 0x6f, 0x62, 0x61, 0x72]); }); /* "foobar" */
if(typeof Buffer !== 'undefined') it('CP 708 : sbcs', function() { chkde(708, Buffer_from([0xca, 0x20, 0x61, 0x6e, 0x64, 0x20, 0xcb, 0x20, 0x73, 0x6d, 0x69, 0x6c, 0x65, 0x79, 0x20, 0x66, 0x61, 0x63, 0x65, 0x73])); }); /* ("ت and ث smiley faces") */
it('CP 936 : dbcs', function() { chkde(936, [0xd5, 0xe2, 0xca, 0xc7, 0xd6, 0xd0, 0xce, 0xc4, 0xd7, 0xd6, 0xb7, 0xfb, 0xb2, 0xe2, 0xca, 0xd4]);}); /* "这是中文字符测试" */
});
});
```
The `testfile` helper function reads a file and compares to node's read facilities:
```>test.js
function testfile(f,cp,type,skip) {
var d = fs.readFileSync(f);
var x = fs.readFileSync(f, type);
var a = x.split("");
var chk = function(cp) {
var y = cptable.utils.decode(cp, d);
assert.equal(x,y);
var z = cptable.utils.encode(cp, x);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(skip) return;
z = cptable.utils.encode(cp, a);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(f.indexOf("cptable.js") == -1) {
cptable.utils.encode(cp, d, 'str');
cptable.utils.encode(cp, d, 'arr');
}
}
cptable.utils.cache.encache();
chk(cp);
if(skip) return;
cptable.utils.cache.decache();
chk(cp);
cptable.utils.cache.encache();
}
```
The `utf8` tests verify UTF-8 encoding of the actual JS sources:
```>test.js
describe('node natives', function() {
var node = [[65001, 'utf8',1], [1200, 'utf16le',1], [20127, 'ascii',0]];
var unicodefiles = ['codepage.md','README.md','cptable.js'];
var asciifiles = ['cputils.js'];
node.forEach(function(w) {
describe(w[1], function() {
cptable = require('./');
asciifiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(!w[2]) return;
unicodefiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(w[1] === 'utf8') it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(f) { testfile('./bits/' + f,w[0],w[1],true); });
});
});
});
});
```
The `utf*` and `ascii` tests attempt to test other magic formats:
```>test.js
var m = cptable.utils.magic;
function cmp(x,z) {
assert.equal(x.length, z.length);
for(var i = 0; i != z.length; ++i) assert.equal(i+"/"+x.length+""+x[i], i+"/"+z.length+""+z[i]);
}
Object.keys(m).forEach(function(t){if(t != 16969) describe(m[t], function() {
it("should process codepage.md." + m[t], fs.existsSync('./misc/codepage.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/codepage.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/codepage.md.' + m[t]);
var y, z;
cptable.utils.cache.encache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.decache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.encache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.decache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.encache();
}
: null);
it("should process README.md." + m[t], fs.existsSync('./misc/README.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/README.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/README.md.' + m[t]);
x = [].slice.call(x);
cptable.utils.cache.encache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.decache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.encache();
}
: null);
});});
```
The codepage `6969` is not defined, so operations should fail:
```>test.js
describe('failures', function() {
it('should fail to find CP 6969', function() {
assert.throws(function(){cptable[6969].dec});
assert.throws(function(){cptable[6969].enc});
});
it('should fail using utils', function() {
assert(!cptable.utils.hascp(6969));
assert.throws(function(){return cptable.utils.encode(6969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(6969, [0x20]); });
});
it('should fail with black magic', function() {
assert(cptable.utils.hascp(16969));
assert.throws(function(){return cptable.utils.encode(16969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(16969, [0x20]); });
});
it('should fail when presented with invalid char codes', function() {
assert.throws(function(){cptable.utils.cache.decache(); return cptable.utils.encode(20127, [String.fromCharCode(0xAA)]);});
});
it('should fail to propagate UTF8 BOM in UTF7', function() {
["+/v8-abc", "+/v9"].forEach(function(m) { assert.throws(function() {
assert.equal(m, cptable.utils.encode(65000, cptable.utils.decode(65000, m)));
}); });
});
});
```
# Nitty Gritty
```json>package.json
{
"name": "codepage",
"version": "1.14.0",
"author": "SheetJS",
"description": "pure-JS library to handle codepages",
"keywords": [ "codepage", "iconv", "convert", "strings" ],
"bin": {
"codepage": "./bin/codepage.njs"
},
"main": "cputils.js",
"types": "types",
"browser": {
"buffer": "false"
},
"dependencies": {
"commander": "~2.14.1",
"exit-on-epipe": "~1.0.1"
},
"devDependencies": {
"voc": "~1.1.0",
"mocha": "~2.5.3",
"blanket": "~1.2.3",
"@sheetjs/uglify-js": "~2.7.3",
"@types/node": "^8.0.7",
"@types/commander": "^2.12.0",
"dtslint": "^0.1.2",
"typescript": "2.2.0"
},
"repository": { "type":"git", "url":"git://github.com/SheetJS/js-codepage.git"},
"scripts": {
"pretest": "git submodule init && git submodule update",
"test": "make test",
"build": "make js",
"lint": "make fullint",
"dtslint": "dtslint types"
},
"config": {
"blanket": {
"pattern": "[cputils.js]"
}
},
"alex": {
"allow": [
"chinese",
"european",
"german",
"japanese",
"latin"
]
},
"homepage": "http://sheetjs.com/opensource",
"files": [
"LICENSE",
"README.md",
"bin",
"bits/*.js",
"types/index.d.ts",
"types/*.json",
"cptable.js",
"cputils.js",
"dist/sbcs.full.js",
"dist/cpexcel.full.js"
],
"bugs": { "url": "https://github.com/SheetJS/js-codepage/issues" },
"license": "Apache-2.0",
"engines": { "node": ">=0.8" }
}
```
```>.vocrc
{ "post": "make js" }
```
```>.gitignore
node_modules
package-lock.json
*.tgz
.gitignore
codepages/
.vocrc
make.sh
make.njs
misc/coverage.html
codepage_mini.md
ctest/sauce*
```

View File

@ -1,6 +1,6 @@
/* cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[620] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàąçêëèïîćÄĄĘęłôöĆûùŚÖÜ¢Ł¥śƒŹŻóÓńŃźż¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[737] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩαβγδεζηθικλμνξοπρσςτυφχψ░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀ωάέήϊίόύϋώΆΈΉΊΌΎΏ±≥≤ΪΫ÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
@ -973,5 +973,6 @@ return {"enc": e, "dec": d }; })();
cptable[10029] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄĀāÉĄÖÜáąČäčĆć鏟ĎíďĒēĖóėôöõúĚěü†°Ę£§•¶ß®©™ę¨≠ģĮįĪ≤≥īĶ∂∑łĻļĽľĹĺŅņѬ√ńŇ∆«»… ňŐÕőŌ–—“”‘’÷◊ōŔŕŘ‹›řŖŗŠ‚„šŚśÁŤťÍŽžŪÓÔūŮÚůŰűŲųÝýķŻŁżĢˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10079] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûüÝ°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸ¤ÐðÞþý·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙıˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10081] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûü†°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸĞğİıŞş‡·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙ<C39B>ˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[28591] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
// eslint-disable-next-line no-undef
if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = cptable;

1700
cptable.js

File diff suppressed because it is too large Load Diff

View File

@ -1,4 +1,4 @@
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
/*::

View File

@ -1,4 +1,4 @@
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {

191
dist/LICENSE vendored
View File

@ -1,4 +1,192 @@
Copyright (C) 2013-present SheetJS
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "{}"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright (C) 2013-present SheetJS LLC
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
@ -11,4 +199,3 @@ Copyright (C) 2013-present SheetJS
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

View File

@ -1,6 +1,6 @@
/* cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[620] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàąçêëèïîćÄĄĘęłôöĆûùŚÖÜ¢Ł¥śƒŹŻóÓńŃźż¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[737] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩαβγδεζηθικλμνξοπρσςτυφχψ░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀ωάέήϊίόύϋώΆΈΉΊΌΎΏ±≥≤ΪΫ÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
@ -973,9 +973,10 @@ return {"enc": e, "dec": d }; })();
cptable[10029] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄĀāÉĄÖÜáąČäčĆć鏟ĎíďĒēĖóėôöõúĚěü†°Ę£§•¶ß®©™ę¨≠ģĮįĪ≤≥īĶ∂∑łĻļĽľĹĺŅņѬ√ńŇ∆«»… ňŐÕőŌ–—“”‘’÷◊ōŔŕŘ‹›řŖŗŠ‚„šŚśÁŤťÍŽžŪÓÔūŮÚůŰűŲųÝýķŻŁżĢˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10079] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûüÝ°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸ¤ÐðÞþý·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙıˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10081] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûü†°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸĞğİıŞş‡·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙ<C39B>ˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[28591] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
// eslint-disable-next-line no-undef
if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = cptable;
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {

5
dist/cpexcel.js vendored
View File

@ -1,6 +1,6 @@
/* cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cpexcel.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[620] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàąçêëèïîćÄĄĘęłôöĆûùŚÖÜ¢Ł¥śƒŹŻóÓńŃźż¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[737] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩαβγδεζηθικλμνξοπρσςτυφχψ░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀ωάέήϊίόύϋώΆΈΉΊΌΎΏ±≥≤ΪΫ÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
@ -973,5 +973,6 @@ return {"enc": e, "dec": d }; })();
cptable[10029] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄĀāÉĄÖÜáąČäčĆć鏟ĎíďĒēĖóėôöõúĚěü†°Ę£§•¶ß®©™ę¨≠ģĮįĪ≤≥īĶ∂∑łĻļĽľĹĺŅņѬ√ńŇ∆«»… ňŐÕőŌ–—“”‘’÷◊ōŔŕŘ‹›řŖŗŠ‚„šŚśÁŤťÍŽžŪÓÔūŮÚůŰűŲųÝýķŻŁżĢˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10079] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûüÝ°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸ¤ÐðÞþý·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙıˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[10081] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÄÅÇÉÑÖÜáàâäãåçéèêëíìîïñóòôöõúùûü†°¢£§•¶ß®©™´¨≠ÆØ∞±≤≥¥µ∂∑∏π∫ªºΩæø¿¡¬√ƒ≈∆«»… ÀÃÕŒœ—“”÷◊ÿŸĞğİıŞş‡·„‰ÂÊÁËÈÍÎÏÌÓÔ<C393>ÒÚÛÙ<C39B>ˆ˜¯˘˙˚¸˝˛ˇ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[28591] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§¨©ª«¬­®¯°±²³´µ¶·¸¹º»¼½¾¿ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõö÷øùúûüýþÿ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
// eslint-disable-next-line no-undef
if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = cptable;

1702
dist/cptable.full.js vendored

File diff suppressed because it is too large Load Diff

1700
dist/cptable.js vendored

File diff suppressed because it is too large Load Diff

2
dist/cputils.js vendored
View File

@ -1,4 +1,4 @@
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {

6
dist/sbcs.full.js vendored
View File

@ -1,6 +1,6 @@
/* sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[37] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ¢.<(+|&éêëèíîïìß!$*);¬-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®^£¥·©§¶¼½¾[]¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[500] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ[.<(+!&éêëèíîïìß]$*);^-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
@ -109,7 +109,7 @@ cptable[620] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\
cptable[895] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ČüéďäĎŤčěĚĹÍľǪÄÁÉžŽôöÓůÚýÖÜŠĽÝŘťáíóúňŇŮÔšřŕŔ¼§«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
// eslint-disable-next-line no-undef
if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = cptable;
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {

4
dist/sbcs.js vendored
View File

@ -1,6 +1,6 @@
/* sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[37] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ¢.<(+|&éêëèíîïìß!$*);¬-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®^£¥·©§¶¼½¾[]¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[500] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ[.<(+!&éêëèíîïìß]$*);^-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();

View File

@ -29,3 +29,4 @@
10029,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT,1
10079,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT,1
10081,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT,1
28591,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT,1

1 437 http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT 1
29 10029 http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT 1
30 10079 http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT 1
31 10081 http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT 1
32 28591 http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT 1

View File

@ -1,4 +1,6 @@
<!DOCTYPE html>
<!-- codepage (C) 2013-present SheetJS http://sheetjs.com -->
<!-- vim: set ts=2: -->
<html>
<head>
<title>js-codepage tests</title>

51
make.njs Normal file
View File

@ -0,0 +1,51 @@
#!/usr/bin/env node
var argv = process.argv.slice(1), fs = require('fs');
if(argv.length < 2) {
console.error("usage: make.njs <codepage_index> [variable]");
process.exit(22); /* EINVAL */
}
var cp/*:string*/ = argv[1];
var jsvar/*:string*/ = argv[2] || "cptable";
var x/*:string*/ = fs.readFileSync("codepages/" + cp + ".TBL","utf8");
var maxcp = 0, i = 0, ii = 0;
var y/*:Array<Array<number> >*/ = x.split("\n").map(function(z/*:string*/)/*:Array<number>*/ {
var w/*:Array<string>*/ = z.split("\t");
if(w.length < 2) return [Number(w[0])];
return [Number(w[0]), Number(w[1])];
}).filter(function(z) { return z.length > 1; });
for(i = 0; i != y.length; ++i) if(y[i][0] > maxcp) maxcp = y[i][0];
var enc/*:{[key:string]:number}*/ = {}, dec/*:{[key:string]:string}|Array<string>*/ = (maxcp < 256 ? [] : {});
for(i = 0; i != y.length; ++i) {
/*:: if(Array.isArray(dec)) */ dec[y[i][0]] = String.fromCharCode(y[i][1]);
enc[String.fromCharCode(y[i][1])] = y[i][0];
}
var odec = "", outstr = "";
if(maxcp < 256) {
/*:: if(Array.isArray(dec)) { */
for(i = 0; i != 256; ++i) if(typeof dec[i] === "undefined") dec[i] = String.fromCharCode(0xFFFD);
odec = JSON.stringify(dec.join(""));
outstr = '(function(){ var d = ' + odec + ', D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();';
/*:: } */
} else {
var dd = [];
/*:: if(!Array.isArray(dec)) { */
for(i in dec) if(dec.hasOwnProperty(i)) {
ii = +i;
if(typeof dd[ii >> 8] === "undefined") dd[ii >> 8] = [];
dd[ii >> 8][ii % 256] = dec[i];
}
/*:: } */
outstr = '(function(){ var d = [], e = {}, D = [], j;\n';
for(var i = 0; i != 256; ++i) if(dd[i]) {
for(var j = 0; j != 256; ++j) if(typeof dd[i][j] === "undefined") dd[i][j] = String.fromCharCode(0xFFFD);
outstr += 'D[' + i + '] = ' + JSON.stringify(dd[i].join("")) + '.split("");\n';
outstr += 'for(j = 0; j != D[' + i + '].length; ++j) if(D[' + i + '][j].charCodeAt(0) !== 0xFFFD) { e[D[' + i + '][j]] = ' + (i*256) + ' + j; d[' + (i*256) + ' + j] = D[' + i + '][j];}\n'
}
outstr += 'return {"enc": e, "dec": d }; })();';
}
process.stdout.write(jsvar + "[" + cp + "] = " + outstr + "\n");

26
make.sh Normal file
View File

@ -0,0 +1,26 @@
#!/bin/bash
INFILE=${1:-pages.csv}
OUTFILE=${2:-cptable.js}
JSVAR=${3:-cptable}
VERSION=$(cat package.json | grep version | tr -dc [0-9.])
mkdir -p codepages bits
rm -f $OUTFILE $OUTFILE.tmp
echo "/*! $OUTFILE (C) 2013-present SheetJS -- http://sheetjs.com */" > $OUTFILE.tmp
echo "/*jshint -W100 */" >> $OUTFILE.tmp
echo "var $JSVAR = {version:\"$VERSION\"};" >> $OUTFILE.tmp
if [ -e dotnet.sh ]; then bash dotnet.sh; fi
awk -F, '{print $1, $2, $3}' $INFILE | while read cp url cptype; do
echo $cp $url
if [ ! -e codepages/$cp.TBL ]; then
curl $url | sed 's/#.*//g' | awk 'NF==2' > codepages/$cp.TBL
fi
echo "if(typeof $JSVAR === 'undefined') $JSVAR = {};" > bits/$cp.js.tmp
node make.njs $cp $JSVAR | tee -a bits/$cp.js.tmp >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <bits/$cp.js.tmp >bits/$cp.js
rm -f bits/$cp.js.tmp
done
echo "// eslint-disable-next-line no-undef" >> $OUTFILE.tmp
echo "if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = $JSVAR;" >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <$OUTFILE.tmp >$OUTFILE
rm -f $OUTFILE.tmp

View File

@ -26,7 +26,7 @@ Alternatively, use the full version in the dist folder:
```
The complete set of codepages is large due to some Double Byte Character Set
encodings. A much smaller file that just includes SBCS codepages is provided in
encodings. A much smaller file that only includes SBCS codepages is provided in
this repo (`sbcs.js`), as well as a file for other projects (`cpexcel.js`)
If you know which codepages you need, you can include individual scripts for
@ -133,7 +133,7 @@ to produce a complete script like `cpexcel.full.js`.
## Building the complete script
This script uses [voc](npm.im/voc). The script to build the codepage tables and
the JS source is `codepage.md`, so building is as simple as `voc codepage.md`.
the JS source is `codepage.md`, so building involves `voc codepage.md`.
## Generated Codepages
@ -274,11 +274,11 @@ tables are not generated, there is no corresponding entry (they are "magic").
| `29001` | Windows 7 | Europa 3 |
| `38598` | Windows 7 | ISO 8859-8 Hebrew (ISO-Logical) |
| `47451` | unicode.org | Atari ST/TT |
| `50220` | Windows 7 | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | Windows 7 | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | Windows 7 | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | Windows 7 | ISO 2022 Korean |
| `50227` | Windows 7 | ISO 2022 Simplified Chinese |
| `50220` | magic | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | magic | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | magic | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | magic | ISO 2022 Korean |
| `50227` | magic | ISO 2022 Simplified Chinese |
| `51932` | Windows 7 | EUC Japanese |
| `51936` | Windows 7 | EUC Simplified Chinese |
| `51949` | Windows 7 | EUC Korean |
@ -330,6 +330,9 @@ To update the browser artifacts, run `make ctest`.
- [Windows Code Page Enumeration](http://msdn.microsoft.com/en-us/library/cc195051.aspx)
- [Windows Code Page Identifiers](http://msdn.microsoft.com/en-us/library/windows/desktop/dd317756.aspx)
- [IBM Coded Character Sets](https://www-01.ibm.com/software/globalization/ccsid/ccsid_registered.html)
- [ISO/IEC 2022 / ECMA-35](https://www.ecma-international.org/publications/files/ECMA-ST/Ecma-035.pdf)
- [International Register of Coded Character Sets To Be Used With Escape Sequences](https://www.itscj.ipsj.or.jp/itscj_english/iso-ir/ISO-IR.pdf)
- [Japanese Character Encoding for Internet Messages](https://tools.ietf.org/html/rfc1468)
## License

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -26,7 +26,7 @@ Alternatively, use the full version in the dist folder:
+AGAAYABg
The complete set of codepages is large due to some Double Byte Character Set
encodings. A much smaller file that just includes SBCS codepages is provided in
encodings. A much smaller file that only includes SBCS codepages is provided in
this repo (+AGA-sbcs.js+AGA), as well as a file for other projects (+AGA-cpexcel.js+AGA)
If you know which codepages you need, you can include individual scripts for
@ -133,7 +133,7 @@ to produce a complete script like +AGA-cpexcel.full.js+AGA.
+ACMAIw Building the complete script
This script uses +AFs-voc+AF0(npm.im/voc). The script to build the codepage tables and
the JS source is +AGA-codepage.md+AGA, so building is as simple as +AGA-voc codepage.md+AGA.
the JS source is +AGA-codepage.md+AGA, so building involves +AGA-voc codepage.md+AGA.
+ACMAIw Generated Codepages
@ -274,11 +274,11 @@ tables are not generated, there is no corresponding entry (they are +ACI-magic+A
+AHw +AGA-29001+AGA +AHw Windows 7 +AHw Europa 3 +AHw
+AHw +AGA-38598+AGA +AHw Windows 7 +AHw ISO 8859-8 Hebrew (ISO-Logical) +AHw
+AHw +AGA-47451+AGA +AHw unicode.org +AHw Atari ST/TT +AHw
+AHw +AGA-50220+AGA +AHw Windows 7 +AHw ISO 2022 JIS Japanese with no halfwidth Katakana +AHw
+AHw +AGA-50221+AGA +AHw Windows 7 +AHw ISO 2022 JIS Japanese with halfwidth Katakana +AHw
+AHw +AGA-50222+AGA +AHw Windows 7 +AHw ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)+AHw
+AHw +AGA-50225+AGA +AHw Windows 7 +AHw ISO 2022 Korean +AHw
+AHw +AGA-50227+AGA +AHw Windows 7 +AHw ISO 2022 Simplified Chinese +AHw
+AHw +AGA-50220+AGA +AHw magic +AHw ISO 2022 JIS Japanese with no halfwidth Katakana +AHw
+AHw +AGA-50221+AGA +AHw magic +AHw ISO 2022 JIS Japanese with halfwidth Katakana +AHw
+AHw +AGA-50222+AGA +AHw magic +AHw ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)+AHw
+AHw +AGA-50225+AGA +AHw magic +AHw ISO 2022 Korean +AHw
+AHw +AGA-50227+AGA +AHw magic +AHw ISO 2022 Simplified Chinese +AHw
+AHw +AGA-51932+AGA +AHw Windows 7 +AHw EUC Japanese +AHw
+AHw +AGA-51936+AGA +AHw Windows 7 +AHw EUC Simplified Chinese +AHw
+AHw +AGA-51949+AGA +AHw Windows 7 +AHw EUC Korean +AHw
@ -330,6 +330,9 @@ To update the browser artifacts, run +AGA-make ctest+AGA.
- +AFs-Windows Code Page Enumeration+AF0(http://msdn.microsoft.com/en-us/library/cc195051.aspx)
- +AFs-Windows Code Page Identifiers+AF0(http://msdn.microsoft.com/en-us/library/windows/desktop/dd317756.aspx)
- +AFs-IBM Coded Character Sets+AF0(https://www-01.ibm.com/software/globalization/ccsid/ccsid+AF8-registered.html)
- +AFs-ISO/IEC 2022 / ECMA-35+AF0(https://www.ecma-international.org/publications/files/ECMA-ST/Ecma-035.pdf)
- +AFs-International Register of Coded Character Sets To Be Used With Escape Sequences+AF0(https://www.itscj.ipsj.or.jp/itscj+AF8-english/iso-ir/ISO-IR.pdf)
- +AFs-Japanese Character Encoding for Internet Messages+AF0(https://tools.ietf.org/html/rfc1468)
+ACMAIw License

View File

@ -26,7 +26,7 @@ Alternatively, use the full version in the dist folder:
```
The complete set of codepages is large due to some Double Byte Character Set
encodings. A much smaller file that just includes SBCS codepages is provided in
encodings. A much smaller file that only includes SBCS codepages is provided in
this repo (`sbcs.js`), as well as a file for other projects (`cpexcel.js`)
If you know which codepages you need, you can include individual scripts for
@ -133,7 +133,7 @@ to produce a complete script like `cpexcel.full.js`.
## Building the complete script
This script uses [voc](npm.im/voc). The script to build the codepage tables and
the JS source is `codepage.md`, so building is as simple as `voc codepage.md`.
the JS source is `codepage.md`, so building involves `voc codepage.md`.
## Generated Codepages
@ -274,11 +274,11 @@ tables are not generated, there is no corresponding entry (they are "magic").
| `29001` | Windows 7 | Europa 3 |
| `38598` | Windows 7 | ISO 8859-8 Hebrew (ISO-Logical) |
| `47451` | unicode.org | Atari ST/TT |
| `50220` | Windows 7 | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | Windows 7 | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | Windows 7 | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | Windows 7 | ISO 2022 Korean |
| `50227` | Windows 7 | ISO 2022 Simplified Chinese |
| `50220` | magic | ISO 2022 JIS Japanese with no halfwidth Katakana |
| `50221` | magic | ISO 2022 JIS Japanese with halfwidth Katakana |
| `50222` | magic | ISO 2022 Japanese JIS X 0201-1989 (1 byte Kana-SO/SI)|
| `50225` | magic | ISO 2022 Korean |
| `50227` | magic | ISO 2022 Simplified Chinese |
| `51932` | Windows 7 | EUC Japanese |
| `51936` | Windows 7 | EUC Simplified Chinese |
| `51949` | Windows 7 | EUC Korean |
@ -330,6 +330,9 @@ To update the browser artifacts, run `make ctest`.
- [Windows Code Page Enumeration](http://msdn.microsoft.com/en-us/library/cc195051.aspx)
- [Windows Code Page Identifiers](http://msdn.microsoft.com/en-us/library/windows/desktop/dd317756.aspx)
- [IBM Coded Character Sets](https://www-01.ibm.com/software/globalization/ccsid/ccsid_registered.html)
- [ISO/IEC 2022 / ECMA-35](https://www.ecma-international.org/publications/files/ECMA-ST/Ecma-035.pdf)
- [International Register of Coded Character Sets To Be Used With Escape Sequences](https://www.itscj.ipsj.or.jp/itscj_english/iso-ir/ISO-IR.pdf)
- [Japanese Character Encoding for Internet Messages](https://tools.ietf.org/html/rfc1468)
## License

View File

@ -2,78 +2,14 @@
The fields of the `pages.csv` manifest are `codepage,url,bytes` (SBCS=1, DBCS=2)
```>pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
863,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP863.TXT,1
864,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP864.TXT,1
865,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP865.TXT,1
866,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP866.TXT,1
869,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP869.TXT,1
874,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT,1
875,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT,1
932,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT,2
936,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP936.TXT,2
949,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT,2
950,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT,2
1026,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT,1
1250,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT,1
1251,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT,1
1252,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT,1
1253,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT,1
1254,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT,1
1255,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT,1
1256,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT,1
1257,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT,1
1258,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT,1
47451,http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/ATARIST.TXT,1
```
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private `0xF8FF` code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. Codepages are an absolute pain :/
```>pages.csv
10000,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ROMAN.TXT,1
10006,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/GREEK.TXT,1
10007,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT,1
10029,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT,1
10079,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT,1
10081,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT,1
```
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the `ISO-8859-X` series is `28590 + X`:
```>pages.csv
28591,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT,1
28592,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-2.TXT,1
28593,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-3.TXT,1
28594,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-4.TXT,1
28595,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-5.TXT,1
28596,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-6.TXT,1
28597,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT,1
28598,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-8.TXT,1
28599,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-9.TXT,1
28600,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT,1
28601,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT,1
28603,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT,1
28604,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT,1
28605,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT,1
28606,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT,1
```
## Generated Codepages
The following codepages are available in .NET on Windows:
@ -142,11 +78,6 @@ The following codepages are available in .NET on Windows:
- 21866 Ukrainian (KOI8-U); Cyrillic (KOI8-U)
- 29001 Europa 3
- 38598 ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
- 50220 ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
- 50221 ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS Allow 1 byte Kana)
- 50222 ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS Allow 1 byte Kana - SO/SI)
- 50225 ISO 2022 Korean
- 50227 ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
- 51932 EUC Japanese
- 51936 EUC Simplified Chinese; Chinese Simplified (EUC)
- 51949 EUC Korean
@ -163,107 +94,11 @@ The following codepages are available in .NET on Windows:
- 57010 ISCII Gujarati
- 57011 ISCII Punjabi
```>pages.csv
708,,1
720,,1
808,,1
858,,1
870,,1
872,,1
1010,,1
1047,,1
1132,,1
1140,,1
1141,,1
1142,,1
1143,,1
1144,,1
1145,,1
1146,,1
1147,,1
1148,,1
1149,,1
1361,,2
10001,,2
10002,,2
10003,,2
10004,,1
10005,,1
10008,,2
10010,,1
10017,,1
10021,,1
10082,,1
20000,,2
20001,,2
20002,,2
20003,,2
20004,,2
20005,,2
20105,,1
20106,,1
20107,,1
20108,,1
20261,,2
20269,,1
20273,,1
20277,,1
20278,,1
20280,,1
20284,,1
20285,,1
20290,,1
20297,,1
20420,,1
20423,,1
20424,,1
20833,,1
20838,,1
20866,,1
20871,,1
20880,,1
20905,,1
20924,,1
20932,,2
20936,,2
20949,,2
21025,,1
21027,,1
21866,,1
29001,,1
38598,,1
50220,,2
50221,,2
50222,,2
50225,,2
50227,,2
51932,,2
51936,,2
51949,,2
52936,,2
54936,,2
57002,,2
57003,,2
57004,,2
57005,,2
57006,,2
57007,,2
57008,,2
57009,,2
57010,,2
57011,,2
```
The following codepages are dependencies for Visual FoxPro:
- 620 Mazovia (Polish) MS-DOS
- 895 Kamenick (Czech) MS-DOS
```>pages.csv
620,,1
895,,1
```
## Building Notes
The script `make.sh` (described later) will get these files and massage the data
@ -289,13 +124,7 @@ which implies that code `0xF6` is `String.fromCharCode(0x02C6)` and vice versa.
To build the sources on windows, consult `dotnet/MakeEncoding.cs`.
After saving the standard output to `out`, a simple script processes the result:
```>dotnet.sh
#!/bin/bash
if [ ! -e dotnet/out ]; then exit; fi
<dotnet/out tr -s ' ' '\t' | awk 'NF>2 {if(outfile) close(outfile); outfile="codepages/" $1 ".TBL"} NF==2 {print > outfile}'
```
After saving standard output to `out`, the `dotnet.sh` script processes results.
# Building the script
@ -304,43 +133,9 @@ generates JS code for encoding and decoding:
## Raw Codepages
```>make.njs
#!/usr/bin/env node
var argv = process.argv.slice(1), fs = require('fs');
if(argv.length < 2) {
console.error("usage: make.njs <codepage_index> [variable]");
process.exit(22); /* EINVAL */
}
var cp/*:string*/ = argv[1];
var jsvar/*:string*/ = argv[2] || "cptable";
var x/*:string*/ = fs.readFileSync("codepages/" + cp + ".TBL","utf8");
var maxcp = 0, i = 0, ii = 0;
var y/*:Array<Array<number> >*/ = x.split("\n").map(function(z/*:string*/)/*:Array<number>*/ {
var w/*:Array<string>*/ = z.split("\t");
if(w.length < 2) return [Number(w[0])];
return [Number(w[0]), Number(w[1])];
}).filter(function(z) { return z.length > 1; });
```
The DBCS and SBCS code generation strategies are different. The maximum code is
used to distinguish (max `0xFF` for SBCS).
```
for(i = 0; i != y.length; ++i) if(y[i][0] > maxcp) maxcp = y[i][0];
var enc/*:{[key:string]:number}*/ = {}, dec/*:{[key:string]:string}|Array<string>*/ = (maxcp < 256 ? [] : {});
for(i = 0; i != y.length; ++i) {
/*:: if(Array.isArray(dec)) */ dec[y[i][0]] = String.fromCharCode(y[i][1]);
enc[String.fromCharCode(y[i][1])] = y[i][0];
}
var odec = "", outstr = "";
if(maxcp < 256) {
/*:: if(Array.isArray(dec)) { */
```
The Unicode character `0xFFFD` (REPLACEMENT CHARACTER) is used as a placeholder
for characters that are not specified in the map (for example, `0xF0` is not in
code page 10000).
@ -348,14 +143,6 @@ code page 10000).
For SBCS, the idea is to embed a raw string with the contents of the 256 codes.
The `dec` field is merely a split of the string, and `enc` is an eversion:
```
for(i = 0; i != 256; ++i) if(typeof dec[i] === "undefined") dec[i] = String.fromCharCode(0xFFFD);
odec = JSON.stringify(dec.join(""));
outstr = '(function(){ var d = ' + odec + ', D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();';
/*:: } */
} else {
```
DBCS is similar, except that the space is sliced in chunks of 256 bytes (strings
are only generated for those high-bytes represented in the codepage).
@ -363,27 +150,6 @@ The strategy is to construct an array-of-arrays so that `dd[high][low]` is the
character associated with the code. This array is combined at runtime to yield
the complete decoding object (and the encoding object is an eversion):
```
var dd = [];
/*:: if(!Array.isArray(dec)) { */
for(i in dec) if(dec.hasOwnProperty(i)) {
ii = +i;
if(typeof dd[ii >> 8] === "undefined") dd[ii >> 8] = [];
dd[ii >> 8][ii % 256] = dec[i];
}
/*:: } */
outstr = '(function(){ var d = [], e = {}, D = [], j;\n';
for(var i = 0; i != 256; ++i) if(dd[i]) {
for(var j = 0; j != 256; ++j) if(typeof dd[i][j] === "undefined") dd[i][j] = String.fromCharCode(0xFFFD);
outstr += 'D[' + i + '] = ' + JSON.stringify(dd[i].join("")) + '.split("");\n';
outstr += 'for(j = 0; j != D[' + i + '].length; ++j) if(D[' + i + '][j].charCodeAt(0) !== 0xFFFD) { e[D[' + i + '][j]] = ' + (i*256) + ' + j; d[' + (i*256) + ' + j] = D[' + i + '][j];}\n'
}
outstr += 'return {"enc": e, "dec": d }; })();';
}
process.stdout.write(jsvar + "[" + cp + "] = " + outstr + "\n");
```
`make.sh` generates the tables used by `make.njs`. The raw Unicode TXT files
are columnar: `code unicode #comments`. For example, the last 10 lines of the
text file `ROMAN.TXT` (for CP 10000) are:
@ -404,35 +170,6 @@ text file `ROMAN.TXT` (for CP 10000) are:
In processing the data, the comments (after the `#`) are stripped and undefined
elements (like `0x7F` for CP 10000) are removed.
```>make.sh
#!/bin/bash
INFILE=${1:-pages.csv}
OUTFILE=${2:-cptable.js}
JSVAR=${3:-cptable}
VERSION=$(cat package.json | grep version | tr -dc [0-9.])
mkdir -p codepages bits
rm -f $OUTFILE $OUTFILE.tmp
echo "/* $OUTFILE (C) 2013-present SheetJS -- http://sheetjs.com */" > $OUTFILE.tmp
echo "/*jshint -W100 */" >> $OUTFILE.tmp
echo "var $JSVAR = {version:\"$VERSION\"};" >> $OUTFILE.tmp
if [ -e dotnet.sh ]; then bash dotnet.sh; fi
awk -F, '{print $1, $2, $3}' $INFILE | while read cp url cptype; do
echo $cp $url
if [ ! -e codepages/$cp.TBL ]; then
curl $url | sed 's/#.*//g' | awk 'NF==2' > codepages/$cp.TBL
fi
echo "if(typeof $JSVAR === 'undefined') $JSVAR = {};" > bits/$cp.js.tmp
node make.njs $cp $JSVAR | tee -a bits/$cp.js.tmp >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <bits/$cp.js.tmp >bits/$cp.js
rm -f bits/$cp.js.tmp
done
echo "// eslint-disable-next-line no-undef" >> $OUTFILE.tmp
echo "if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = $JSVAR;" >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <$OUTFILE.tmp >$OUTFILE
rm -f $OUTFILE.tmp
```
## Utilities
The encode and decode functions are kept in a separate script (`cputils.js`).
@ -446,412 +183,8 @@ Both encode and decode deal with data represented as:
The `ofmt` variable controls `encode` output (`str`, `arr` respectively)
while the input format is automatically determined.
# Tests
```>test.js
var fs = require('fs'), assert = require('assert'), vm = require('vm');
var cptable, sbcs;
```
Due to a bug in `Buffer.from` in node `4.0 - 4.4`, a special check is needed:
```>test.js
var Buffer_from = function(){};
if(typeof Buffer !== 'undefined') {
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
}
```
The tests include JS validity tests (requiring or evaluating code):
```>test.js
describe('source', function() {
it('should load node', function() { cptable = require('./'); });
it('should load sbcs', function() { sbcs = require('./sbcs'); });
it('should load excel', function() { excel = require('./cpexcel'); });
it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(x) {
vm.runInThisContext(fs.readFileSync('./bits/' + x));
});
});
});
```
The README tests verify the snippets in the README:
```>test.js
describe('README', function() {
var readme = function() {
var unicode_cp10000_255 = cptable[10000].dec[255]; //
assert.equal(unicode_cp10000_255, "");
var cp10000_711 = cptable[10000].enc[String.fromCharCode(711)]; // 255
assert.equal(cp10000_711, 255);
var b1 = [0xbb,0xe3,0xd7,0xdc];
var s1 = b1.map(function(x) { return String.fromCharCode(x); }).join("");
var = cptable.utils.decode(936, b1);
var buf = cptable.utils.encode(936, );
assert.equal(,"");
assert.equal(buf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b1[i], buf[i]);
var b2 = [0xf0,0x9f,0x8d,0xa3];
var sushi= cptable.utils.decode(65001, b2);
var sbuf = cptable.utils.encode(65001, sushi);
assert.equal(sushi,"");
assert.equal(sbuf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b2[i], sbuf[i]);
};
it('should be correct', function() {
cptable.utils.cache.encache();
readme();
cptable.utils.cache.decache();
readme();
});
});
```
The consistency tests make sure that encoding and decoding are pseudo inverses:
```>test.js
describe('consistency', function() {
cptable = require('./');
U = cptable.utils;
var chk = function(cptable, cacheit) { return function(x) {
it('should consistently process CP ' + x, function() {
var cp = cptable[x], D = cp.dec, E = cp.enc;
if(cacheit) cptable.utils.cache.encache();
else cptable.utils.cache.decache();
Object.keys(D).forEach(function(d) {
if(E[D[d]] != d) {
if(typeof E[D[d]] !== "undefined") return;
if(D[d].charCodeAt(0) == 0xFFFD) return;
if(D[E[D[d]]] === D[d]) return;
throw new Error(x + " e.d[" + d + "] = " + E[D[d]] + "; d[" + d + "]=" + D[d] + "; d.e.d[" + d + "] = " + D[E[D[d]]]);
}
});
Object.keys(E).forEach(function(e) {
if(D[E[e]] != e) {
throw new Error(x + " d.e[" + e + "] = " + D[E[e]] + "; e[" + e + "]=" + E[e] + "; e.d.e[" + e + "] = " + E[D[E[e]]]);
}
});
var corpus = ["foobar"];
corpus.forEach(function(w){
assert.equal(U.decode(x,U.encode(x,w)),w);
});
cptable.utils.cache.encache();
});
}; };
describe('cached', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, true));
});
describe('direct', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, false));
});
});
```
The next tests look at possible entry conditions:
```
describe('entry conditions', function() {
it('should fail to load utils if cptable unavailable', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
assert.throws(function() {
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
});
it('should load utils if cptable is available', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
vm.runInContext(fs.readFileSync('cpexcel.js','utf8'),ctx);
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
var chken = function(cp, i) {
var c = function(cp, i, e) {
var str = cptable.utils.encode(cp,i,e);
var arr = cptable.utils.encode(cp,i.split(""),e);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.encode(cp,Buffer_from(i),e);
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
cptable.utils.cache.decache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
};
describe('encode', function() {
it('CP 1252 : sbcs', function() { chken(1252,"foobr"); });
it('CP 708 : sbcs', function() { chken(708," and smiley faces");});
it('CP 936 : dbcs', function() { chken(936, "");});
});
var chkde = function(cp, i) {
var c = function(cp, i) {
var s;
if(typeof Buffer !== 'undefined' && i instanceof Buffer) s = [].map.call(i, function(s){return String.fromCharCode(s); });
else s=(i.map) ? i.map(function(s){return String.fromCharCode(s); }) : i;
var str = cptable.utils.decode(cp,i);
var arr = cptable.utils.decode(cp,s.join?s.join(""):s);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.decode(cp,Buffer_from(i));
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
cptable.utils.cache.decache();
c(cp,i);
};
describe('decode', function() {
it('CP 1252 : sbcs', function() { chkde(1252,[0x66, 0x6f, 0x6f, 0x62, 0x61, 0x72]); }); /* "foobar" */
if(typeof Buffer !== 'undefined') it('CP 708 : sbcs', function() { chkde(708, Buffer_from([0xca, 0x20, 0x61, 0x6e, 0x64, 0x20, 0xcb, 0x20, 0x73, 0x6d, 0x69, 0x6c, 0x65, 0x79, 0x20, 0x66, 0x61, 0x63, 0x65, 0x73])); }); /* (" and smiley faces") */
it('CP 936 : dbcs', function() { chkde(936, [0xd5, 0xe2, 0xca, 0xc7, 0xd6, 0xd0, 0xce, 0xc4, 0xd7, 0xd6, 0xb7, 0xfb, 0xb2, 0xe2, 0xca, 0xd4]);}); /* "" */
});
});
```
The `testfile` helper function reads a file and compares to node's read facilities:
```>test.js
function testfile(f,cp,type,skip) {
var d = fs.readFileSync(f);
var x = fs.readFileSync(f, type);
var a = x.split("");
var chk = function(cp) {
var y = cptable.utils.decode(cp, d);
assert.equal(x,y);
var z = cptable.utils.encode(cp, x);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(skip) return;
z = cptable.utils.encode(cp, a);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(f.indexOf("cptable.js") == -1) {
cptable.utils.encode(cp, d, 'str');
cptable.utils.encode(cp, d, 'arr');
}
}
cptable.utils.cache.encache();
chk(cp);
if(skip) return;
cptable.utils.cache.decache();
chk(cp);
cptable.utils.cache.encache();
}
```
The `utf8` tests verify UTF-8 encoding of the actual JS sources:
```>test.js
describe('node natives', function() {
var node = [[65001, 'utf8',1], [1200, 'utf16le',1], [20127, 'ascii',0]];
var unicodefiles = ['codepage.md','README.md','cptable.js'];
var asciifiles = ['cputils.js'];
node.forEach(function(w) {
describe(w[1], function() {
cptable = require('./');
asciifiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(!w[2]) return;
unicodefiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(w[1] === 'utf8') it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(f) { testfile('./bits/' + f,w[0],w[1],true); });
});
});
});
});
```
The `utf*` and `ascii` tests attempt to test other magic formats:
```>test.js
var m = cptable.utils.magic;
function cmp(x,z) {
assert.equal(x.length, z.length);
for(var i = 0; i != z.length; ++i) assert.equal(i+"/"+x.length+""+x[i], i+"/"+z.length+""+z[i]);
}
Object.keys(m).forEach(function(t){if(t != 16969) describe(m[t], function() {
it("should process codepage.md." + m[t], fs.existsSync('./misc/codepage.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/codepage.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/codepage.md.' + m[t]);
var y, z;
cptable.utils.cache.encache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.decache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.encache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.decache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.encache();
}
: null);
it("should process README.md." + m[t], fs.existsSync('./misc/README.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/README.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/README.md.' + m[t]);
x = [].slice.call(x);
cptable.utils.cache.encache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.decache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.encache();
}
: null);
});});
```
The codepage `6969` is not defined, so operations should fail:
```>test.js
describe('failures', function() {
it('should fail to find CP 6969', function() {
assert.throws(function(){cptable[6969].dec});
assert.throws(function(){cptable[6969].enc});
});
it('should fail using utils', function() {
assert(!cptable.utils.hascp(6969));
assert.throws(function(){return cptable.utils.encode(6969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(6969, [0x20]); });
});
it('should fail with black magic', function() {
assert(cptable.utils.hascp(16969));
assert.throws(function(){return cptable.utils.encode(16969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(16969, [0x20]); });
});
it('should fail when presented with invalid char codes', function() {
assert.throws(function(){cptable.utils.cache.decache(); return cptable.utils.encode(20127, [String.fromCharCode(0xAA)]);});
});
it('should fail to propagate UTF8 BOM in UTF7', function() {
["+/v8-abc", "+/v9"].forEach(function(m) { assert.throws(function() {
assert.equal(m, cptable.utils.encode(65000, cptable.utils.decode(65000, m)));
}); });
});
});
```
# Nitty Gritty
```json>package.json
{
"name": "codepage",
"version": "1.14.0",
"author": "SheetJS",
"description": "pure-JS library to handle codepages",
"keywords": [ "codepage", "iconv", "convert", "strings" ],
"bin": {
"codepage": "./bin/codepage.njs"
},
"main": "cputils.js",
"types": "types",
"browser": {
"buffer": "false"
},
"dependencies": {
"commander": "~2.14.1",
"exit-on-epipe": "~1.0.1"
},
"devDependencies": {
"voc": "~1.1.0",
"mocha": "~2.5.3",
"blanket": "~1.2.3",
"@sheetjs/uglify-js": "~2.7.3",
"@types/node": "^8.0.7",
"@types/commander": "^2.12.0",
"dtslint": "^0.1.2",
"typescript": "2.2.0"
},
"repository": { "type":"git", "url":"git://github.com/SheetJS/js-codepage.git"},
"scripts": {
"pretest": "git submodule init && git submodule update",
"test": "make test",
"build": "make js",
"lint": "make fullint",
"dtslint": "dtslint types"
},
"config": {
"blanket": {
"pattern": "[cputils.js]"
}
},
"alex": {
"allow": [
"chinese",
"european",
"german",
"japanese",
"latin"
]
},
"homepage": "http://sheetjs.com/opensource",
"files": [
"LICENSE",
"README.md",
"bin",
"bits/*.js",
"types/index.d.ts",
"types/*.json",
"cptable.js",
"cputils.js",
"dist/sbcs.full.js",
"dist/cpexcel.full.js"
],
"bugs": { "url": "https://github.com/SheetJS/js-codepage/issues" },
"license": "Apache-2.0",
"engines": { "node": ">=0.8" }
}
```
```>.vocrc
{ "post": "make js" }
```
```>.gitignore
node_modules
package-lock.json
*.tgz
.gitignore
codepages/
.vocrc
make.sh
make.njs
misc/coverage.html
codepage_mini.md
ctest/sauce*
```

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -2,78 +2,14 @@
The fields of the +AGA-pages.csv+AGA manifest are +AGA-codepage,url,bytes+AGA (SBCS+AD0-1, DBCS+AD0-2)
+AGAAYABgAD4-pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
863,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP863.TXT,1
864,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP864.TXT,1
865,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP865.TXT,1
866,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP866.TXT,1
869,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP869.TXT,1
874,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT,1
875,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT,1
932,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT,2
936,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP936.TXT,2
949,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT,2
950,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT,2
1026,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT,1
1250,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT,1
1251,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT,1
1252,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT,1
1253,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT,1
1254,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT,1
1255,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT,1
1256,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT,1
1257,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT,1
1258,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT,1
47451,http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/ATARIST.TXT,1
+AGAAYABg
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private +AGA-0xF8FF+AGA code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. Codepages are an absolute pain :/
+AGAAYABgAD4-pages.csv
10000,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ROMAN.TXT,1
10006,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/GREEK.TXT,1
10007,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT,1
10029,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT,1
10079,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT,1
10081,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT,1
+AGAAYABg
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the +AGA-ISO-8859-X+AGA series is +AGA-28590 +- X+AGA:
+AGAAYABgAD4-pages.csv
28591,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT,1
28592,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-2.TXT,1
28593,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-3.TXT,1
28594,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-4.TXT,1
28595,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-5.TXT,1
28596,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-6.TXT,1
28597,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT,1
28598,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-8.TXT,1
28599,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-9.TXT,1
28600,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT,1
28601,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT,1
28603,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT,1
28604,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT,1
28605,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT,1
28606,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT,1
+AGAAYABg
+ACMAIw Generated Codepages
The following codepages are available in .NET on Windows:
@ -142,11 +78,6 @@ The following codepages are available in .NET on Windows:
- 21866 Ukrainian (KOI8-U)+ADs Cyrillic (KOI8-U)
- 29001 Europa 3
- 38598 ISO 8859-8 Hebrew+ADs Hebrew (ISO-Logical)
- 50220 ISO 2022 Japanese with no halfwidth Katakana+ADs Japanese (JIS)
- 50221 ISO 2022 Japanese with halfwidth Katakana+ADs Japanese (JIS Allow 1 byte Kana)
- 50222 ISO 2022 Japanese JIS X 0201-1989+ADs Japanese (JIS Allow 1 byte Kana - SO/SI)
- 50225 ISO 2022 Korean
- 50227 ISO 2022 Simplified Chinese+ADs Chinese Simplified (ISO 2022)
- 51932 EUC Japanese
- 51936 EUC Simplified Chinese+ADs Chinese Simplified (EUC)
- 51949 EUC Korean
@ -163,107 +94,11 @@ The following codepages are available in .NET on Windows:
- 57010 ISCII Gujarati
- 57011 ISCII Punjabi
+AGAAYABgAD4-pages.csv
708,,1
720,,1
808,,1
858,,1
870,,1
872,,1
1010,,1
1047,,1
1132,,1
1140,,1
1141,,1
1142,,1
1143,,1
1144,,1
1145,,1
1146,,1
1147,,1
1148,,1
1149,,1
1361,,2
10001,,2
10002,,2
10003,,2
10004,,1
10005,,1
10008,,2
10010,,1
10017,,1
10021,,1
10082,,1
20000,,2
20001,,2
20002,,2
20003,,2
20004,,2
20005,,2
20105,,1
20106,,1
20107,,1
20108,,1
20261,,2
20269,,1
20273,,1
20277,,1
20278,,1
20280,,1
20284,,1
20285,,1
20290,,1
20297,,1
20420,,1
20423,,1
20424,,1
20833,,1
20838,,1
20866,,1
20871,,1
20880,,1
20905,,1
20924,,1
20932,,2
20936,,2
20949,,2
21025,,1
21027,,1
21866,,1
29001,,1
38598,,1
50220,,2
50221,,2
50222,,2
50225,,2
50227,,2
51932,,2
51936,,2
51949,,2
52936,,2
54936,,2
57002,,2
57003,,2
57004,,2
57005,,2
57006,,2
57007,,2
57008,,2
57009,,2
57010,,2
57011,,2
+AGAAYABg
The following codepages are dependencies for Visual FoxPro:
- 620 Mazovia (Polish) MS-DOS
- 895 Kamenick+AP0 (Czech) MS-DOS
+AGAAYABgAD4-pages.csv
620,,1
895,,1
+AGAAYABg
+ACMAIw Building Notes
The script +AGA-make.sh+AGA (described later) will get these files and massage the data
@ -289,13 +124,7 @@ which implies that code +AGA-0xF6+AGA is +AGA-String.fromCharCode(0x02C6)+AGA an
To build the sources on windows, consult +AGA-dotnet/MakeEncoding.cs+AGA.
After saving the standard output to +AGA-out+AGA, a simple script processes the result:
+AGAAYABgAD4-dotnet.sh
+ACMAIQ-/bin/bash
if +AFs +ACE -e dotnet/out +AF0AOw then exit+ADs fi
+ADw-dotnet/out tr -s ' ' '+AFw-t' +AHw awk 'NF+AD4-2 +AHs-if(outfile) close(outfile)+ADs outfile+AD0AIg-codepages/+ACI +ACQ-1 +ACI.TBL+ACIAfQ NF+AD0APQ-2 +AHs-print +AD4 outfile+AH0'
+AGAAYABg
After saving standard output to +AGA-out+AGA, the +AGA-dotnet.sh+AGA script processes results.
+ACM Building the script
@ -304,43 +133,9 @@ generates JS code for encoding and decoding:
+ACMAIw Raw Codepages
+AGAAYABgAD4-make.njs
+ACMAIQ-/usr/bin/env node
var argv +AD0 process.argv.slice(1), fs +AD0 require('fs')+ADs
if(argv.length +ADw 2) +AHs
console.error(+ACI-usage: make.njs +ADw-codepage+AF8-index+AD4 +AFs-variable+AF0AIg)+ADs
process.exit(22)+ADs /+ACo EINVAL +ACo-/
+AH0
var cp/+ACo:string+ACo-/ +AD0 argv+AFs-1+AF0AOw
var jsvar/+ACo:string+ACo-/ +AD0 argv+AFs-2+AF0 +AHwAfA +ACI-cptable+ACIAOw
var x/+ACo:string+ACo-/ +AD0 fs.readFileSync(+ACI-codepages/+ACI +- cp +- +ACI.TBL+ACI,+ACI-utf8+ACI)+ADs
var maxcp +AD0 0, i +AD0 0, ii +AD0 0+ADs
var y/+ACo:Array+ADw-Array+ADw-number+AD4 +AD4AKg-/ +AD0 x.split(+ACIAXA-n+ACI).map(function(z/+ACo:string+ACo-/)/+ACo:Array+ADw-number+AD4AKg-/ +AHs
var w/+ACo:Array+ADw-string+AD4AKg-/ +AD0 z.split(+ACIAXA-t+ACI)+ADs
if(w.length +ADw 2) return +AFs-Number(w+AFs-0+AF0)+AF0AOw
return +AFs-Number(w+AFs-0+AF0), Number(w+AFs-1+AF0)+AF0AOw
+AH0).filter(function(z) +AHs return z.length +AD4 1+ADs +AH0)+ADs
+AGAAYABg
The DBCS and SBCS code generation strategies are different. The maximum code is
used to distinguish (max +AGA-0xFF+AGA for SBCS).
+AGAAYABg
for(i +AD0 0+ADs i +ACEAPQ y.length+ADs +-+-i) if(y+AFs-i+AF0AWw-0+AF0 +AD4 maxcp) maxcp +AD0 y+AFs-i+AF0AWw-0+AF0AOw
var enc/+ACo:+AHsAWw-key:string+AF0:number+AH0AKg-/ +AD0 +AHsAfQ, dec/+ACo:+AHsAWw-key:string+AF0:string+AH0AfA-Array+ADw-string+AD4AKg-/ +AD0 (maxcp +ADw 256 ? +AFsAXQ : +AHsAfQ)+ADs
for(i +AD0 0+ADs i +ACEAPQ y.length+ADs +-+-i) +AHs
/+ACo:: if(Array.isArray(dec)) +ACo-/ dec+AFs-y+AFs-i+AF0AWw-0+AF0AXQ +AD0 String.fromCharCode(y+AFs-i+AF0AWw-1+AF0)+ADs
enc+AFs-String.fromCharCode(y+AFs-i+AF0AWw-1+AF0)+AF0 +AD0 y+AFs-i+AF0AWw-0+AF0AOw
+AH0
var odec +AD0 +ACIAIg, outstr +AD0 +ACIAIgA7
if(maxcp +ADw 256) +AHs
/+ACo:: if(Array.isArray(dec)) +AHs +ACo-/
+AGAAYABg
The Unicode character +AGA-0xFFFD+AGA (REPLACEMENT CHARACTER) is used as a placeholder
for characters that are not specified in the map (for example, +AGA-0xF0+AGA is not in
code page 10000).
@ -348,14 +143,6 @@ code page 10000).
For SBCS, the idea is to embed a raw string with the contents of the 256 codes.
The +AGA-dec+AGA field is merely a split of the string, and +AGA-enc+AGA is an eversion:
+AGAAYABg
for(i +AD0 0+ADs i +ACEAPQ 256+ADs +-+-i) if(typeof dec+AFs-i+AF0 +AD0APQA9 +ACI-undefined+ACI) dec+AFs-i+AF0 +AD0 String.fromCharCode(0xFFFD)+ADs
odec +AD0 JSON.stringify(dec.join(+ACIAIg))+ADs
outstr +AD0 '(function()+AHs var d +AD0 ' +- odec +- ', D +AD0 +AFsAXQ, e +AD0 +AHsAfQA7 for(var i+AD0-0+ADs-i+ACEAPQ-d.length+ADsAKwAr-i) +AHs if(d.charCodeAt(i) +ACEAPQA9 0xFFFD) e+AFs-d.charAt(i)+AF0 +AD0 i+ADs D+AFs-i+AF0 +AD0 d.charAt(i)+ADs +AH0 return +AHsAIg-enc+ACI: e, +ACI-dec+ACI: D +AH0AOw +AH0)()+ADs'+ADs
/+ACo:: +AH0 +ACo-/
+AH0 else +AHs
+AGAAYABg
DBCS is similar, except that the space is sliced in chunks of 256 bytes (strings
are only generated for those high-bytes represented in the codepage).
@ -363,27 +150,6 @@ The strategy is to construct an array-of-arrays so that +AGA-dd+AFs-high+AF0AWw-
character associated with the code. This array is combined at runtime to yield
the complete decoding object (and the encoding object is an eversion):
+AGAAYABg
var dd +AD0 +AFsAXQA7
/+ACo:: if(+ACE-Array.isArray(dec)) +AHs +ACo-/
for(i in dec) if(dec.hasOwnProperty(i)) +AHs
ii +AD0 +-i+ADs
if(typeof dd+AFs-ii +AD4APg 8+AF0 +AD0APQA9 +ACI-undefined+ACI) dd+AFs-ii +AD4APg 8+AF0 +AD0 +AFsAXQA7
dd+AFs-ii +AD4APg 8+AF0AWw-ii +ACU 256+AF0 +AD0 dec+AFs-i+AF0AOw
+AH0
/+ACo:: +AH0 +ACo-/
outstr +AD0 '(function()+AHs var d +AD0 +AFsAXQ, e +AD0 +AHsAfQ, D +AD0 +AFsAXQ, j+ADsAXA-n'+ADs
for(var i +AD0 0+ADs i +ACEAPQ 256+ADs +-+-i) if(dd+AFs-i+AF0) +AHs
for(var j +AD0 0+ADs j +ACEAPQ 256+ADs +-+-j) if(typeof dd+AFs-i+AF0AWw-j+AF0 +AD0APQA9 +ACI-undefined+ACI) dd+AFs-i+AF0AWw-j+AF0 +AD0 String.fromCharCode(0xFFFD)+ADs
outstr +-+AD0 'D+AFs' +- i +- '+AF0 +AD0 ' +- JSON.stringify(dd+AFs-i+AF0.join(+ACIAIg)) +- '.split(+ACIAIg)+ADsAXA-n'+ADs
outstr +-+AD0 'for(j +AD0 0+ADs j +ACEAPQ D+AFs' +- i +- '+AF0.length+ADs +-+-j) if(D+AFs' +- i +- '+AF0AWw-j+AF0.charCodeAt(0) +ACEAPQA9 0xFFFD) +AHs e+AFs-D+AFs' +- i +- '+AF0AWw-j+AF0AXQ +AD0 ' +- (i+ACo-256) +- ' +- j+ADs d+AFs' +- (i+ACo-256) +- ' +- j+AF0 +AD0 D+AFs' +- i +- '+AF0AWw-j+AF0AOwB9AFw-n'
+AH0
outstr +-+AD0 'return +AHsAIg-enc+ACI: e, +ACI-dec+ACI: d +AH0AOw +AH0)()+ADs'+ADs
+AH0
process.stdout.write(jsvar +- +ACIAWwAi +- cp +- +ACIAXQ +AD0 +ACI +- outstr +- +ACIAXA-n+ACI)+ADs
+AGAAYABg
+AGA-make.sh+AGA generates the tables used by +AGA-make.njs+AGA. The raw Unicode TXT files
are columnar: +AGA-code unicode +ACM-comments+AGA. For example, the last 10 lines of the
text file +AGA-ROMAN.TXT+AGA (for CP 10000) are:
@ -404,35 +170,6 @@ text file +AGA-ROMAN.TXT+AGA (for CP 10000) are:
In processing the data, the comments (after the +AGAAIwBg) are stripped and undefined
elements (like +AGA-0x7F+AGA for CP 10000) are removed.
+AGAAYABgAD4-make.sh
+ACMAIQ-/bin/bash
INFILE+AD0AJAB7-1:-pages.csv+AH0
OUTFILE+AD0AJAB7-2:-cptable.js+AH0
JSVAR+AD0AJAB7-3:-cptable+AH0
VERSION+AD0AJA(cat package.json +AHw grep version +AHw tr -dc +AFs-0-9.+AF0)
mkdir -p codepages bits
rm -f +ACQ-OUTFILE +ACQ-OUTFILE.tmp
echo +ACI-/+ACo +ACQ-OUTFILE (C) 2013-present SheetJS -- http://sheetjs.com +ACo-/+ACI +AD4 +ACQ-OUTFILE.tmp
echo +ACI-/+ACo-jshint -W100 +ACo-/+ACI +AD4APg +ACQ-OUTFILE.tmp
echo +ACI-var +ACQ-JSVAR +AD0 +AHs-version:+AFwAIgAk-VERSION+AFwAIgB9ADsAIg +AD4APg +ACQ-OUTFILE.tmp
if +AFs -e dotnet.sh +AF0AOw then bash dotnet.sh+ADs fi
awk -F, '+AHs-print +ACQ-1, +ACQ-2, +ACQ-3+AH0' +ACQ-INFILE +AHw while read cp url cptype+ADs do
echo +ACQ-cp +ACQ-url
if +AFs +ACE -e codepages/+ACQ-cp.TBL +AF0AOw then
curl +ACQ-url +AHw sed 's/+ACM.+ACo-//g' +AHw awk 'NF+AD0APQ-2' +AD4 codepages/+ACQ-cp.TBL
fi
echo +ACI-if(typeof +ACQ-JSVAR +AD0APQA9 'undefined') +ACQ-JSVAR +AD0 +AHsAfQA7ACI +AD4 bits/+ACQ-cp.js.tmp
node make.njs +ACQ-cp +ACQ-JSVAR +AHw tee -a bits/+ACQ-cp.js.tmp +AD4APg +ACQ-OUTFILE.tmp
sed 's/+ACIAXA(+AFs-0-9+AF0AKwBc)+ACI:/+AFw-1:/g' +ADw-bits/+ACQ-cp.js.tmp +AD4-bits/+ACQ-cp.js
rm -f bits/+ACQ-cp.js.tmp
done
echo +ACI-// eslint-disable-next-line no-undef+ACI +AD4APg +ACQ-OUTFILE.tmp
echo +ACI-if (typeof module +ACEAPQA9 'undefined' +ACYAJg module.exports +ACYAJg typeof DO+AF8-NOT+AF8-EXPORT+AF8-CODEPAGE +AD0APQA9 'undefined') module.exports +AD0 +ACQ-JSVAR+ADsAIg +AD4APg +ACQ-OUTFILE.tmp
sed 's/+ACIAXA(+AFs-0-9+AF0AKwBc)+ACI:/+AFw-1:/g' +ADwAJA-OUTFILE.tmp +AD4AJA-OUTFILE
rm -f +ACQ-OUTFILE.tmp
+AGAAYABg
+ACMAIw Utilities
The encode and decode functions are kept in a separate script (+AGA-cputils.js+AGA).
@ -446,412 +183,8 @@ Both encode and decode deal with data represented as:
The +AGA-ofmt+AGA variable controls +AGA-encode+AGA output (+AGA-str+AGA, +AGA-arr+AGA respectively)
while the input format is automatically determined.
+ACM Tests
+AGAAYABgAD4-test.js
var fs +AD0 require('fs'), assert +AD0 require('assert'), vm +AD0 require('vm')+ADs
var cptable, sbcs+ADs
+AGAAYABg
Due to a bug in +AGA-Buffer.from+AGA in node +AGA-4.0 - 4.4+AGA, a special check is needed:
+AGAAYABgAD4-test.js
var Buffer+AF8-from +AD0 function()+AHsAfQA7
if(typeof Buffer +ACEAPQA9 'undefined') +AHs
var nbfs +AD0 +ACE-Buffer.from+ADs
if(+ACE-nbfs) try +AHs Buffer.from(+ACI-foo+ACI, +ACI-utf8+ACI)+ADs +AH0 catch(e) +AHs nbfs +AD0 true+ADs +AH0
Buffer+AF8-from +AD0 nbfs ? function(buf, enc) +AHs return (enc) ? new Buffer(buf, enc) : new Buffer(buf)+ADs +AH0 : Buffer.from.bind(Buffer)+ADs
+AH0
+AGAAYABg
The tests include JS validity tests (requiring or evaluating code):
+AGAAYABgAD4-test.js
describe('source', function() +AHs
it('should load node', function() +AHs cptable +AD0 require('./')+ADs +AH0)+ADs
it('should load sbcs', function() +AHs sbcs +AD0 require('./sbcs')+ADs +AH0)+ADs
it('should load excel', function() +AHs excel +AD0 require('./cpexcel')+ADs +AH0)+ADs
it('should process bits', function() +AHs
var files +AD0 fs.readdirSync('bits').filter(function(x)+AHs-return x.substr(-3)+AD0APQAi.js+ACIAOwB9)+ADs
files.forEach(function(x) +AHs
vm.runInThisContext(fs.readFileSync('./bits/' +- x))+ADs
+AH0)+ADs
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
The README tests verify the snippets in the README:
+AGAAYABgAD4-test.js
describe('README', function() +AHs
var readme +AD0 function() +AHs
var unicode+AF8-cp10000+AF8-255 +AD0 cptable+AFs-10000+AF0.dec+AFs-255+AF0AOw // +Asc
assert.equal(unicode+AF8-cp10000+AF8-255, +ACICxwAi)+ADs
var cp10000+AF8-711 +AD0 cptable+AFs-10000+AF0.enc+AFs-String.fromCharCode(711)+AF0AOw // 255
assert.equal(cp10000+AF8-711, 255)+ADs
var b1 +AD0 +AFs-0xbb,0xe3,0xd7,0xdc+AF0AOw
var s1 +AD0 b1.map(function(x) +AHs return String.fromCharCode(x)+ADs +AH0).join(+ACIAIg)+ADs
var +bEdgOw +AD0 cptable.utils.decode(936, b1)+ADs
var buf +AD0 cptable.utils.encode(936, +bEdgOw)+ADs
assert.equal(+bEdgOw,+ACJsR2A7ACI)+ADs
assert.equal(buf.length, 4)+ADs
for(var i +AD0 0+ADs i +ACEAPQ 4+ADs +-+-i) assert.equal(b1+AFs-i+AF0, buf+AFs-i+AF0)+ADs
var b2 +AD0 +AFs-0xf0,0x9f,0x8d,0xa3+AF0AOw
var sushi+AD0 cptable.utils.decode(65001, b2)+ADs
var sbuf +AD0 cptable.utils.encode(65001, sushi)+ADs
assert.equal(sushi,+ACLYPN9jACI)+ADs
assert.equal(sbuf.length, 4)+ADs
for(var i +AD0 0+ADs i +ACEAPQ 4+ADs +-+-i) assert.equal(b2+AFs-i+AF0, sbuf+AFs-i+AF0)+ADs
+AH0AOw
it('should be correct', function() +AHs
cptable.utils.cache.encache()+ADs
readme()+ADs
cptable.utils.cache.decache()+ADs
readme()+ADs
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
The consistency tests make sure that encoding and decoding are pseudo inverses:
+AGAAYABgAD4-test.js
describe('consistency', function() +AHs
cptable +AD0 require('./')+ADs
U +AD0 cptable.utils+ADs
var chk +AD0 function(cptable, cacheit) +AHs return function(x) +AHs
it('should consistently process CP ' +- x, function() +AHs
var cp +AD0 cptable+AFs-x+AF0, D +AD0 cp.dec, E +AD0 cp.enc+ADs
if(cacheit) cptable.utils.cache.encache()+ADs
else cptable.utils.cache.decache()+ADs
Object.keys(D).forEach(function(d) +AHs
if(E+AFs-D+AFs-d+AF0AXQ +ACEAPQ d) +AHs
if(typeof E+AFs-D+AFs-d+AF0AXQ +ACEAPQA9 +ACI-undefined+ACI) return+ADs
if(D+AFs-d+AF0.charCodeAt(0) +AD0APQ 0xFFFD) return+ADs
if(D+AFs-E+AFs-D+AFs-d+AF0AXQBd +AD0APQA9 D+AFs-d+AF0) return+ADs
throw new Error(x +- +ACI e.d+AFsAIg +- d +- +ACIAXQ +AD0 +ACI +- E+AFs-D+AFs-d+AF0AXQ +- +ACIAOw d+AFsAIg +- d +- +ACIAXQA9ACI +- D+AFs-d+AF0 +- +ACIAOw d.e.d+AFsAIg +- d +- +ACIAXQ +AD0 +ACI +- D+AFs-E+AFs-D+AFs-d+AF0AXQBd)+ADs
+AH0
+AH0)+ADs
Object.keys(E).forEach(function(e) +AHs
if(D+AFs-E+AFs-e+AF0AXQ +ACEAPQ e) +AHs
throw new Error(x +- +ACI d.e+AFsAIg +- e +- +ACIAXQ +AD0 +ACI +- D+AFs-E+AFs-e+AF0AXQ +- +ACIAOw e+AFsAIg +- e +- +ACIAXQA9ACI +- E+AFs-e+AF0 +- +ACIAOw e.d.e+AFsAIg +- e +- +ACIAXQ +AD0 +ACI +- E+AFs-D+AFs-E+AFs-e+AF0AXQBd)+ADs
+AH0
+AH0)+ADs
var corpus +AD0 +AFsAIg-foobar+ACIAXQA7
corpus.forEach(function(w)+AHs
assert.equal(U.decode(x,U.encode(x,w)),w)+ADs
+AH0)+ADs
cptable.utils.cache.encache()+ADs
+AH0)+ADs
+AH0AOw +AH0AOw
describe('cached', function() +AHs
Object.keys(cptable).filter(function(w) +AHs return w +AD0APQ +-w+ADs +AH0).forEach(chk(cptable, true))+ADs
+AH0)+ADs
describe('direct', function() +AHs
Object.keys(cptable).filter(function(w) +AHs return w +AD0APQ +-w+ADs +AH0).forEach(chk(cptable, false))+ADs
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
The next tests look at possible entry conditions:
+AGAAYABg
describe('entry conditions', function() +AHs
it('should fail to load utils if cptable unavailable', function() +AHs
var sandbox +AD0 +AHsAfQA7
var ctx +AD0 vm.createContext(sandbox)+ADs
assert.throws(function() +AHs
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx)+ADs
+AH0)+ADs
+AH0)+ADs
it('should load utils if cptable is available', function() +AHs
var sandbox +AD0 +AHsAfQA7
var ctx +AD0 vm.createContext(sandbox)+ADs
vm.runInContext(fs.readFileSync('cpexcel.js','utf8'),ctx)+ADs
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx)+ADs
+AH0)+ADs
var chken +AD0 function(cp, i) +AHs
var c +AD0 function(cp, i, e) +AHs
var str +AD0 cptable.utils.encode(cp,i,e)+ADs
var arr +AD0 cptable.utils.encode(cp,i.split(+ACIAIg),e)+ADs
assert.deepEqual(str,arr)+ADs
if(typeof Buffer +AD0APQA9 'undefined') return+ADs
var buf +AD0 cptable.utils.encode(cp,Buffer+AF8-from(i),e)+ADs
assert.deepEqual(str,buf)+ADs
+AH0AOw
cptable.utils.cache.encache()+ADs
c(cp,i)+ADs
c(cp,i,'buf')+ADs
c(cp,i,'arr')+ADs
c(cp,i,'str')+ADs
cptable.utils.cache.decache()+ADs
c(cp,i)+ADs
c(cp,i,'buf')+ADs
c(cp,i,'arr')+ADs
c(cp,i,'str')+ADs
+AH0AOw
describe('encode', function() +AHs
it('CP 1252 : sbcs', function() +AHs chken(1252,+ACI-foo+ICI-b+AP4-r+ACI)+ADs +AH0)+ADs
it('CP 708 : sbcs', function() +AHs chken(708,+ACIGKg and +Bis smiley faces+ACI)+ADsAfQ)+ADs
it('CP 936 : dbcs', function() +AHs chken(936, +ACKP2WYvTi1lh1tXeyZtS4vVACI)+ADsAfQ)+ADs
+AH0)+ADs
var chkde +AD0 function(cp, i) +AHs
var c +AD0 function(cp, i) +AHs
var s+ADs
if(typeof Buffer +ACEAPQA9 'undefined' +ACYAJg i instanceof Buffer) s +AD0 +AFsAXQ.map.call(i, function(s)+AHs-return String.fromCharCode(s)+ADs +AH0)+ADs
else s+AD0(i.map) ? i.map(function(s)+AHs-return String.fromCharCode(s)+ADs +AH0) : i+ADs
var str +AD0 cptable.utils.decode(cp,i)+ADs
var arr +AD0 cptable.utils.decode(cp,s.join?s.join(+ACIAIg):s)+ADs
assert.deepEqual(str,arr)+ADs
if(typeof Buffer +AD0APQA9 'undefined') return+ADs
var buf +AD0 cptable.utils.decode(cp,Buffer+AF8-from(i))+ADs
assert.deepEqual(str,buf)+ADs
+AH0AOw
cptable.utils.cache.encache()+ADs
c(cp,i)+ADs
cptable.utils.cache.decache()+ADs
c(cp,i)+ADs
+AH0AOw
describe('decode', function() +AHs
it('CP 1252 : sbcs', function() +AHs chkde(1252,+AFs-0x66, 0x6f, 0x6f, 0x62, 0x61, 0x72+AF0)+ADs +AH0)+ADs /+ACo +ACI-foobar+ACI +ACo-/
if(typeof Buffer +ACEAPQA9 'undefined') it('CP 708 : sbcs', function() +AHs chkde(708, Buffer+AF8-from(+AFs-0xca, 0x20, 0x61, 0x6e, 0x64, 0x20, 0xcb, 0x20, 0x73, 0x6d, 0x69, 0x6c, 0x65, 0x79, 0x20, 0x66, 0x61, 0x63, 0x65, 0x73+AF0))+ADs +AH0)+ADs /+ACo (+ACIGKg and +Bis smiley faces+ACI) +ACo-/
it('CP 936 : dbcs', function() +AHs chkde(936, +AFs-0xd5, 0xe2, 0xca, 0xc7, 0xd6, 0xd0, 0xce, 0xc4, 0xd7, 0xd6, 0xb7, 0xfb, 0xb2, 0xe2, 0xca, 0xd4+AF0)+ADsAfQ)+ADs /+ACo +ACKP2WYvTi1lh1tXeyZtS4vVACI +ACo-/
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
The +AGA-testfile+AGA helper function reads a file and compares to node's read facilities:
+AGAAYABgAD4-test.js
function testfile(f,cp,type,skip) +AHs
var d +AD0 fs.readFileSync(f)+ADs
var x +AD0 fs.readFileSync(f, type)+ADs
var a +AD0 x.split(+ACIAIg)+ADs
var chk +AD0 function(cp) +AHs
var y +AD0 cptable.utils.decode(cp, d)+ADs
assert.equal(x,y)+ADs
var z +AD0 cptable.utils.encode(cp, x)+ADs
if(z.length +ACEAPQ d.length) throw new Error(f +- +ACI +ACI +- JSON.stringify(z) +- +ACI +ACEAPQ +ACI +- JSON.stringify(d) +- +ACI : +ACI +- z.length +- +ACI +ACI +- d.length)+ADs
for(var i +AD0 0+ADs i +ACEAPQ d.length+ADs +-+-i) if(d+AFs-i+AF0 +ACEAPQA9 z+AFs-i+AF0) throw new Error(+ACIAIg +- i +- +ACI +ACI +- d+AFs-i+AF0 +- +ACIAIQA9ACI +- z+AFs-i+AF0)+ADs
if(skip) return+ADs
z +AD0 cptable.utils.encode(cp, a)+ADs
if(z.length +ACEAPQ d.length) throw new Error(f +- +ACI +ACI +- JSON.stringify(z) +- +ACI +ACEAPQ +ACI +- JSON.stringify(d) +- +ACI : +ACI +- z.length +- +ACI +ACI +- d.length)+ADs
for(var i +AD0 0+ADs i +ACEAPQ d.length+ADs +-+-i) if(d+AFs-i+AF0 +ACEAPQA9 z+AFs-i+AF0) throw new Error(+ACIAIg +- i +- +ACI +ACI +- d+AFs-i+AF0 +- +ACIAIQA9ACI +- z+AFs-i+AF0)+ADs
if(f.indexOf(+ACI-cptable.js+ACI) +AD0APQ -1) +AHs
cptable.utils.encode(cp, d, 'str')+ADs
cptable.utils.encode(cp, d, 'arr')+ADs
+AH0
+AH0
cptable.utils.cache.encache()+ADs
chk(cp)+ADs
if(skip) return+ADs
cptable.utils.cache.decache()+ADs
chk(cp)+ADs
cptable.utils.cache.encache()+ADs
+AH0
+AGAAYABg
The +AGA-utf8+AGA tests verify UTF-8 encoding of the actual JS sources:
+AGAAYABgAD4-test.js
describe('node natives', function() +AHs
var node +AD0 +AFsAWw-65001, 'utf8',1+AF0, +AFs-1200, 'utf16le',1+AF0, +AFs-20127, 'ascii',0+AF0AXQA7
var unicodefiles +AD0 +AFs'codepage.md','README.md','cptable.js'+AF0AOw
var asciifiles +AD0 +AFs'cputils.js'+AF0AOw
node.forEach(function(w) +AHs
describe(w+AFs-1+AF0, function() +AHs
cptable +AD0 require('./')+ADs
asciifiles.forEach(function(f) +AHs
it('should process ' +- f, function() +AHs testfile('./misc/'+-f+-'.'+-w+AFs-1+AF0,w+AFs-0+AF0,w+AFs-1+AF0)+ADs +AH0)+ADs
+AH0)+ADs
if(+ACE-w+AFs-2+AF0) return+ADs
unicodefiles.forEach(function(f) +AHs
it('should process ' +- f, function() +AHs testfile('./misc/'+-f+-'.'+-w+AFs-1+AF0,w+AFs-0+AF0,w+AFs-1+AF0)+ADs +AH0)+ADs
+AH0)+ADs
if(w+AFs-1+AF0 +AD0APQA9 'utf8') it('should process bits', function() +AHs
var files +AD0 fs.readdirSync('bits').filter(function(x)+AHs-return x.substr(-3)+AD0APQAi.js+ACIAOwB9)+ADs
files.forEach(function(f) +AHs testfile('./bits/' +- f,w+AFs-0+AF0,w+AFs-1+AF0,true)+ADs +AH0)+ADs
+AH0)+ADs
+AH0)+ADs
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
The +AGA-utf+ACoAYA and +AGA-ascii+AGA tests attempt to test other magic formats:
+AGAAYABgAD4-test.js
var m +AD0 cptable.utils.magic+ADs
function cmp(x,z) +AHs
assert.equal(x.length, z.length)+ADs
for(var i +AD0 0+ADs i +ACEAPQ z.length+ADs +-+-i) assert.equal(i+-+ACI-/+ACIAKw-x.length+-+ACIAIgAr-x+AFs-i+AF0, i+-+ACI-/+ACIAKw-z.length+-+ACIAIgAr-z+AFs-i+AF0)+ADs
+AH0
Object.keys(m).forEach(function(t)+AHs-if(t +ACEAPQ 16969) describe(m+AFs-t+AF0, function() +AHs
it(+ACI-should process codepage.md.+ACI +- m+AFs-t+AF0, fs.existsSync('./misc/codepage.md.' +- m+AFs-t+AF0) ?
function() +AHs
var b +AD0 fs.readFileSync('./misc/codepage.md.utf8', +ACI-utf8+ACI)+ADs
if(m+AFs-t+AF0 +AD0APQA9 +ACI-ascii+ACI) b +AD0 b.replace(/+AFsAXA-u0080-+AFw-uffff+AF0AKg-/g,+ACIAIg)+ADs
var x +AD0 fs.readFileSync('./misc/codepage.md.' +- m+AFs-t+AF0)+ADs
var y, z+ADs
cptable.utils.cache.encache()+ADs
y +AD0 cptable.utils.decode(t, x)+ADs
assert.equal(y,b)+ADs
z +AD0 cptable.utils.encode(t, y)+ADs
if(t +ACEAPQ 65000) cmp(x,z)+ADs
else +AHs assert.equal(y, cptable.utils.decode(t, z))+ADs +AH0
cptable.utils.cache.decache()+ADs
y +AD0 cptable.utils.decode(t, x)+ADs
assert.equal(y,b)+ADs
z +AD0 cptable.utils.encode(t, y)+ADs
if(t +ACEAPQ 65000) cmp(x,z)+ADs
else +AHs assert.equal(y, cptable.utils.decode(t, z))+ADs +AH0
cptable.utils.cache.encache()+ADs
cptable.utils.encode(t, y, 'str')+ADs
cptable.utils.encode(t, y, 'arr')+ADs
cptable.utils.cache.decache()+ADs
cptable.utils.encode(t, y, 'str')+ADs
cptable.utils.encode(t, y, 'arr')+ADs
cptable.utils.cache.encache()+ADs
+AH0
: null)+ADs
it(+ACI-should process README.md.+ACI +- m+AFs-t+AF0, fs.existsSync('./misc/README.md.' +- m+AFs-t+AF0) ?
function() +AHs
var b +AD0 fs.readFileSync('./misc/README.md.utf8', +ACI-utf8+ACI)+ADs
if(m+AFs-t+AF0 +AD0APQA9 +ACI-ascii+ACI) b +AD0 b.replace(/+AFsAXA-u0080-+AFw-uffff+AF0AKg-/g,+ACIAIg)+ADs
var x +AD0 fs.readFileSync('./misc/README.md.' +- m+AFs-t+AF0)+ADs
x +AD0 +AFsAXQ.slice.call(x)+ADs
cptable.utils.cache.encache()+ADs
var y +AD0 cptable.utils.decode(t, x)+ADs
assert.equal(y,b)+ADs
cptable.utils.cache.decache()+ADs
var y +AD0 cptable.utils.decode(t, x)+ADs
assert.equal(y,b)+ADs
cptable.utils.cache.encache()+ADs
+AH0
: null)+ADs
+AH0)+ADsAfQ)+ADs
+AGAAYABg
The codepage +AGA-6969+AGA is not defined, so operations should fail:
+AGAAYABgAD4-test.js
describe('failures', function() +AHs
it('should fail to find CP 6969', function() +AHs
assert.throws(function()+AHs-cptable+AFs-6969+AF0.dec+AH0)+ADs
assert.throws(function()+AHs-cptable+AFs-6969+AF0.enc+AH0)+ADs
+AH0)+ADs
it('should fail using utils', function() +AHs
assert(+ACE-cptable.utils.hascp(6969))+ADs
assert.throws(function()+AHs-return cptable.utils.encode(6969, +ACI-foobar+ACI)+ADs +AH0)+ADs
assert.throws(function()+AHs-return cptable.utils.decode(6969, +AFs-0x20+AF0)+ADs +AH0)+ADs
+AH0)+ADs
it('should fail with black magic', function() +AHs
assert(cptable.utils.hascp(16969))+ADs
assert.throws(function()+AHs-return cptable.utils.encode(16969, +ACI-foobar+ACI)+ADs +AH0)+ADs
assert.throws(function()+AHs-return cptable.utils.decode(16969, +AFs-0x20+AF0)+ADs +AH0)+ADs
+AH0)+ADs
it('should fail when presented with invalid char codes', function() +AHs
assert.throws(function()+AHs-cptable.utils.cache.decache()+ADs return cptable.utils.encode(20127, +AFs-String.fromCharCode(0xAA)+AF0)+ADsAfQ)+ADs
+AH0)+ADs
it('should fail to propagate UTF8 BOM in UTF7', function() +AHs
+AFsAIgAr-/v8-abc+ACI, +ACIAKw-/v9+ACIAXQ.forEach(function(m) +AHs assert.throws(function() +AHs
assert.equal(m, cptable.utils.encode(65000, cptable.utils.decode(65000, m)))+ADs
+AH0)+ADs +AH0)+ADs
+AH0)+ADs
+AH0)+ADs
+AGAAYABg
+ACM Nitty Gritty
+AGAAYABg-json+AD4-package.json
+AHs
+ACI-name+ACI: +ACI-codepage+ACI,
+ACI-version+ACI: +ACI-1.14.0+ACI,
+ACI-author+ACI: +ACI-SheetJS+ACI,
+ACI-description+ACI: +ACI-pure-JS library to handle codepages+ACI,
+ACI-keywords+ACI: +AFs +ACI-codepage+ACI, +ACI-iconv+ACI, +ACI-convert+ACI, +ACI-strings+ACI +AF0,
+ACI-bin+ACI: +AHs
+ACI-codepage+ACI: +ACI./bin/codepage.njs+ACI
+AH0,
+ACI-main+ACI: +ACI-cputils.js+ACI,
+ACI-types+ACI: +ACI-types+ACI,
+ACI-browser+ACI: +AHs
+ACI-buffer+ACI: +ACI-false+ACI
+AH0,
+ACI-dependencies+ACI: +AHs
+ACI-commander+ACI: +ACIAfg-2.14.1+ACI,
+ACI-exit-on-epipe+ACI: +ACIAfg-1.0.1+ACI
+AH0,
+ACI-devDependencies+ACI: +AHs
+ACI-voc+ACI: +ACIAfg-1.1.0+ACI,
+ACI-mocha+ACI: +ACIAfg-2.5.3+ACI,
+ACI-blanket+ACI: +ACIAfg-1.2.3+ACI,
+ACIAQA-sheetjs/uglify-js+ACI: +ACIAfg-2.7.3+ACI,
+ACIAQA-types/node+ACI: +ACIAXg-8.0.7+ACI,
+ACIAQA-types/commander+ACI: +ACIAXg-2.12.0+ACI,
+ACI-dtslint+ACI: +ACIAXg-0.1.2+ACI,
+ACI-typescript+ACI: +ACI-2.2.0+ACI
+AH0,
+ACI-repository+ACI: +AHs +ACI-type+ACI:+ACI-git+ACI, +ACI-url+ACI:+ACI-git://github.com/SheetJS/js-codepage.git+ACIAfQ,
+ACI-scripts+ACI: +AHs
+ACI-pretest+ACI: +ACI-git submodule init +ACYAJg git submodule update+ACI,
+ACI-test+ACI: +ACI-make test+ACI,
+ACI-build+ACI: +ACI-make js+ACI,
+ACI-lint+ACI: +ACI-make fullint+ACI,
+ACI-dtslint+ACI: +ACI-dtslint types+ACI
+AH0,
+ACI-config+ACI: +AHs
+ACI-blanket+ACI: +AHs
+ACI-pattern+ACI: +ACIAWw-cputils.js+AF0AIg
+AH0
+AH0,
+ACI-alex+ACI: +AHs
+ACI-allow+ACI: +AFs
+ACI-chinese+ACI,
+ACI-european+ACI,
+ACI-german+ACI,
+ACI-japanese+ACI,
+ACI-latin+ACI
+AF0
+AH0,
+ACI-homepage+ACI: +ACI-http://sheetjs.com/opensource+ACI,
+ACI-files+ACI: +AFs
+ACI-LICENSE+ACI,
+ACI-README.md+ACI,
+ACI-bin+ACI,
+ACI-bits/+ACo.js+ACI,
+ACI-types/index.d.ts+ACI,
+ACI-types/+ACo.json+ACI,
+ACI-cptable.js+ACI,
+ACI-cputils.js+ACI,
+ACI-dist/sbcs.full.js+ACI,
+ACI-dist/cpexcel.full.js+ACI
+AF0,
+ACI-bugs+ACI: +AHs +ACI-url+ACI: +ACI-https://github.com/SheetJS/js-codepage/issues+ACI +AH0,
+ACI-license+ACI: +ACI-Apache-2.0+ACI,
+ACI-engines+ACI: +AHs +ACI-node+ACI: +ACIAPgA9-0.8+ACI +AH0
+AH0
+AGAAYABg
+AGAAYABgAD4.vocrc
+AHs +ACI-post+ACI: +ACI-make js+ACI +AH0
+AGAAYABg
+AGAAYABgAD4.gitignore
node+AF8-modules
package-lock.json
+ACo.tgz
.gitignore
codepages/
.vocrc
make.sh
make.njs
misc/coverage.html
codepage+AF8-mini.md
ctest/sauce+ACo
+AGAAYABg

View File

@ -2,78 +2,14 @@
The fields of the `pages.csv` manifest are `codepage,url,bytes` (SBCS=1, DBCS=2)
```>pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
863,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP863.TXT,1
864,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP864.TXT,1
865,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP865.TXT,1
866,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP866.TXT,1
869,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP869.TXT,1
874,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT,1
875,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT,1
932,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP932.TXT,2
936,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP936.TXT,2
949,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP949.TXT,2
950,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT,2
1026,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT,1
1250,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT,1
1251,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT,1
1252,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT,1
1253,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT,1
1254,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT,1
1255,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT,1
1256,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT,1
1257,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT,1
1258,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT,1
47451,http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/ATARIST.TXT,1
```
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private `0xF8FF` code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. Codepages are an absolute pain :/
```>pages.csv
10000,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ROMAN.TXT,1
10006,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/GREEK.TXT,1
10007,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/CYRILLIC.TXT,1
10029,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT,1
10079,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/ICELAND.TXT,1
10081,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/MAC/TURKISH.TXT,1
```
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the `ISO-8859-X` series is `28590 + X`:
```>pages.csv
28591,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-1.TXT,1
28592,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-2.TXT,1
28593,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-3.TXT,1
28594,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-4.TXT,1
28595,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-5.TXT,1
28596,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-6.TXT,1
28597,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-7.TXT,1
28598,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-8.TXT,1
28599,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-9.TXT,1
28600,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-10.TXT,1
28601,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-11.TXT,1
28603,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-13.TXT,1
28604,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-14.TXT,1
28605,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-15.TXT,1
28606,http://www.unicode.org/Public/MAPPINGS/ISO8859/8859-16.TXT,1
```
## Generated Codepages
The following codepages are available in .NET on Windows:
@ -142,11 +78,6 @@ The following codepages are available in .NET on Windows:
- 21866 Ukrainian (KOI8-U); Cyrillic (KOI8-U)
- 29001 Europa 3
- 38598 ISO 8859-8 Hebrew; Hebrew (ISO-Logical)
- 50220 ISO 2022 Japanese with no halfwidth Katakana; Japanese (JIS)
- 50221 ISO 2022 Japanese with halfwidth Katakana; Japanese (JIS Allow 1 byte Kana)
- 50222 ISO 2022 Japanese JIS X 0201-1989; Japanese (JIS Allow 1 byte Kana - SO/SI)
- 50225 ISO 2022 Korean
- 50227 ISO 2022 Simplified Chinese; Chinese Simplified (ISO 2022)
- 51932 EUC Japanese
- 51936 EUC Simplified Chinese; Chinese Simplified (EUC)
- 51949 EUC Korean
@ -163,107 +94,11 @@ The following codepages are available in .NET on Windows:
- 57010 ISCII Gujarati
- 57011 ISCII Punjabi
```>pages.csv
708,,1
720,,1
808,,1
858,,1
870,,1
872,,1
1010,,1
1047,,1
1132,,1
1140,,1
1141,,1
1142,,1
1143,,1
1144,,1
1145,,1
1146,,1
1147,,1
1148,,1
1149,,1
1361,,2
10001,,2
10002,,2
10003,,2
10004,,1
10005,,1
10008,,2
10010,,1
10017,,1
10021,,1
10082,,1
20000,,2
20001,,2
20002,,2
20003,,2
20004,,2
20005,,2
20105,,1
20106,,1
20107,,1
20108,,1
20261,,2
20269,,1
20273,,1
20277,,1
20278,,1
20280,,1
20284,,1
20285,,1
20290,,1
20297,,1
20420,,1
20423,,1
20424,,1
20833,,1
20838,,1
20866,,1
20871,,1
20880,,1
20905,,1
20924,,1
20932,,2
20936,,2
20949,,2
21025,,1
21027,,1
21866,,1
29001,,1
38598,,1
50220,,2
50221,,2
50222,,2
50225,,2
50227,,2
51932,,2
51936,,2
51949,,2
52936,,2
54936,,2
57002,,2
57003,,2
57004,,2
57005,,2
57006,,2
57007,,2
57008,,2
57009,,2
57010,,2
57011,,2
```
The following codepages are dependencies for Visual FoxPro:
- 620 Mazovia (Polish) MS-DOS
- 895 Kamenický (Czech) MS-DOS
```>pages.csv
620,,1
895,,1
```
## Building Notes
The script `make.sh` (described later) will get these files and massage the data
@ -289,13 +124,7 @@ which implies that code `0xF6` is `String.fromCharCode(0x02C6)` and vice versa.
To build the sources on windows, consult `dotnet/MakeEncoding.cs`.
After saving the standard output to `out`, a simple script processes the result:
```>dotnet.sh
#!/bin/bash
if [ ! -e dotnet/out ]; then exit; fi
<dotnet/out tr -s ' ' '\t' | awk 'NF>2 {if(outfile) close(outfile); outfile="codepages/" $1 ".TBL"} NF==2 {print > outfile}'
```
After saving standard output to `out`, the `dotnet.sh` script processes results.
# Building the script
@ -304,43 +133,9 @@ generates JS code for encoding and decoding:
## Raw Codepages
```>make.njs
#!/usr/bin/env node
var argv = process.argv.slice(1), fs = require('fs');
if(argv.length < 2) {
console.error("usage: make.njs <codepage_index> [variable]");
process.exit(22); /* EINVAL */
}
var cp/*:string*/ = argv[1];
var jsvar/*:string*/ = argv[2] || "cptable";
var x/*:string*/ = fs.readFileSync("codepages/" + cp + ".TBL","utf8");
var maxcp = 0, i = 0, ii = 0;
var y/*:Array<Array<number> >*/ = x.split("\n").map(function(z/*:string*/)/*:Array<number>*/ {
var w/*:Array<string>*/ = z.split("\t");
if(w.length < 2) return [Number(w[0])];
return [Number(w[0]), Number(w[1])];
}).filter(function(z) { return z.length > 1; });
```
The DBCS and SBCS code generation strategies are different. The maximum code is
used to distinguish (max `0xFF` for SBCS).
```
for(i = 0; i != y.length; ++i) if(y[i][0] > maxcp) maxcp = y[i][0];
var enc/*:{[key:string]:number}*/ = {}, dec/*:{[key:string]:string}|Array<string>*/ = (maxcp < 256 ? [] : {});
for(i = 0; i != y.length; ++i) {
/*:: if(Array.isArray(dec)) */ dec[y[i][0]] = String.fromCharCode(y[i][1]);
enc[String.fromCharCode(y[i][1])] = y[i][0];
}
var odec = "", outstr = "";
if(maxcp < 256) {
/*:: if(Array.isArray(dec)) { */
```
The Unicode character `0xFFFD` (REPLACEMENT CHARACTER) is used as a placeholder
for characters that are not specified in the map (for example, `0xF0` is not in
code page 10000).
@ -348,14 +143,6 @@ code page 10000).
For SBCS, the idea is to embed a raw string with the contents of the 256 codes.
The `dec` field is merely a split of the string, and `enc` is an eversion:
```
for(i = 0; i != 256; ++i) if(typeof dec[i] === "undefined") dec[i] = String.fromCharCode(0xFFFD);
odec = JSON.stringify(dec.join(""));
outstr = '(function(){ var d = ' + odec + ', D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();';
/*:: } */
} else {
```
DBCS is similar, except that the space is sliced in chunks of 256 bytes (strings
are only generated for those high-bytes represented in the codepage).
@ -363,27 +150,6 @@ The strategy is to construct an array-of-arrays so that `dd[high][low]` is the
character associated with the code. This array is combined at runtime to yield
the complete decoding object (and the encoding object is an eversion):
```
var dd = [];
/*:: if(!Array.isArray(dec)) { */
for(i in dec) if(dec.hasOwnProperty(i)) {
ii = +i;
if(typeof dd[ii >> 8] === "undefined") dd[ii >> 8] = [];
dd[ii >> 8][ii % 256] = dec[i];
}
/*:: } */
outstr = '(function(){ var d = [], e = {}, D = [], j;\n';
for(var i = 0; i != 256; ++i) if(dd[i]) {
for(var j = 0; j != 256; ++j) if(typeof dd[i][j] === "undefined") dd[i][j] = String.fromCharCode(0xFFFD);
outstr += 'D[' + i + '] = ' + JSON.stringify(dd[i].join("")) + '.split("");\n';
outstr += 'for(j = 0; j != D[' + i + '].length; ++j) if(D[' + i + '][j].charCodeAt(0) !== 0xFFFD) { e[D[' + i + '][j]] = ' + (i*256) + ' + j; d[' + (i*256) + ' + j] = D[' + i + '][j];}\n'
}
outstr += 'return {"enc": e, "dec": d }; })();';
}
process.stdout.write(jsvar + "[" + cp + "] = " + outstr + "\n");
```
`make.sh` generates the tables used by `make.njs`. The raw Unicode TXT files
are columnar: `code unicode #comments`. For example, the last 10 lines of the
text file `ROMAN.TXT` (for CP 10000) are:
@ -404,35 +170,6 @@ text file `ROMAN.TXT` (for CP 10000) are:
In processing the data, the comments (after the `#`) are stripped and undefined
elements (like `0x7F` for CP 10000) are removed.
```>make.sh
#!/bin/bash
INFILE=${1:-pages.csv}
OUTFILE=${2:-cptable.js}
JSVAR=${3:-cptable}
VERSION=$(cat package.json | grep version | tr -dc [0-9.])
mkdir -p codepages bits
rm -f $OUTFILE $OUTFILE.tmp
echo "/* $OUTFILE (C) 2013-present SheetJS -- http://sheetjs.com */" > $OUTFILE.tmp
echo "/*jshint -W100 */" >> $OUTFILE.tmp
echo "var $JSVAR = {version:\"$VERSION\"};" >> $OUTFILE.tmp
if [ -e dotnet.sh ]; then bash dotnet.sh; fi
awk -F, '{print $1, $2, $3}' $INFILE | while read cp url cptype; do
echo $cp $url
if [ ! -e codepages/$cp.TBL ]; then
curl $url | sed 's/#.*//g' | awk 'NF==2' > codepages/$cp.TBL
fi
echo "if(typeof $JSVAR === 'undefined') $JSVAR = {};" > bits/$cp.js.tmp
node make.njs $cp $JSVAR | tee -a bits/$cp.js.tmp >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <bits/$cp.js.tmp >bits/$cp.js
rm -f bits/$cp.js.tmp
done
echo "// eslint-disable-next-line no-undef" >> $OUTFILE.tmp
echo "if (typeof module !== 'undefined' && module.exports && typeof DO_NOT_EXPORT_CODEPAGE === 'undefined') module.exports = $JSVAR;" >> $OUTFILE.tmp
sed 's/"\([0-9]+\)":/\1:/g' <$OUTFILE.tmp >$OUTFILE
rm -f $OUTFILE.tmp
```
## Utilities
The encode and decode functions are kept in a separate script (`cputils.js`).
@ -446,412 +183,8 @@ Both encode and decode deal with data represented as:
The `ofmt` variable controls `encode` output (`str`, `arr` respectively)
while the input format is automatically determined.
# Tests
```>test.js
var fs = require('fs'), assert = require('assert'), vm = require('vm');
var cptable, sbcs;
```
Due to a bug in `Buffer.from` in node `4.0 - 4.4`, a special check is needed:
```>test.js
var Buffer_from = function(){};
if(typeof Buffer !== 'undefined') {
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
}
```
The tests include JS validity tests (requiring or evaluating code):
```>test.js
describe('source', function() {
it('should load node', function() { cptable = require('./'); });
it('should load sbcs', function() { sbcs = require('./sbcs'); });
it('should load excel', function() { excel = require('./cpexcel'); });
it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(x) {
vm.runInThisContext(fs.readFileSync('./bits/' + x));
});
});
});
```
The README tests verify the snippets in the README:
```>test.js
describe('README', function() {
var readme = function() {
var unicode_cp10000_255 = cptable[10000].dec[255]; // ˇ
assert.equal(unicode_cp10000_255, "ˇ");
var cp10000_711 = cptable[10000].enc[String.fromCharCode(711)]; // 255
assert.equal(cp10000_711, 255);
var b1 = [0xbb,0xe3,0xd7,0xdc];
var s1 = b1.map(function(x) { return String.fromCharCode(x); }).join("");
var 汇总 = cptable.utils.decode(936, b1);
var buf = cptable.utils.encode(936, 汇总);
assert.equal(汇总,"汇总");
assert.equal(buf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b1[i], buf[i]);
var b2 = [0xf0,0x9f,0x8d,0xa3];
var sushi= cptable.utils.decode(65001, b2);
var sbuf = cptable.utils.encode(65001, sushi);
assert.equal(sushi,"🍣");
assert.equal(sbuf.length, 4);
for(var i = 0; i != 4; ++i) assert.equal(b2[i], sbuf[i]);
};
it('should be correct', function() {
cptable.utils.cache.encache();
readme();
cptable.utils.cache.decache();
readme();
});
});
```
The consistency tests make sure that encoding and decoding are pseudo inverses:
```>test.js
describe('consistency', function() {
cptable = require('./');
U = cptable.utils;
var chk = function(cptable, cacheit) { return function(x) {
it('should consistently process CP ' + x, function() {
var cp = cptable[x], D = cp.dec, E = cp.enc;
if(cacheit) cptable.utils.cache.encache();
else cptable.utils.cache.decache();
Object.keys(D).forEach(function(d) {
if(E[D[d]] != d) {
if(typeof E[D[d]] !== "undefined") return;
if(D[d].charCodeAt(0) == 0xFFFD) return;
if(D[E[D[d]]] === D[d]) return;
throw new Error(x + " e.d[" + d + "] = " + E[D[d]] + "; d[" + d + "]=" + D[d] + "; d.e.d[" + d + "] = " + D[E[D[d]]]);
}
});
Object.keys(E).forEach(function(e) {
if(D[E[e]] != e) {
throw new Error(x + " d.e[" + e + "] = " + D[E[e]] + "; e[" + e + "]=" + E[e] + "; e.d.e[" + e + "] = " + E[D[E[e]]]);
}
});
var corpus = ["foobar"];
corpus.forEach(function(w){
assert.equal(U.decode(x,U.encode(x,w)),w);
});
cptable.utils.cache.encache();
});
}; };
describe('cached', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, true));
});
describe('direct', function() {
Object.keys(cptable).filter(function(w) { return w == +w; }).forEach(chk(cptable, false));
});
});
```
The next tests look at possible entry conditions:
```
describe('entry conditions', function() {
it('should fail to load utils if cptable unavailable', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
assert.throws(function() {
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
});
it('should load utils if cptable is available', function() {
var sandbox = {};
var ctx = vm.createContext(sandbox);
vm.runInContext(fs.readFileSync('cpexcel.js','utf8'),ctx);
vm.runInContext(fs.readFileSync('cputils.js','utf8'),ctx);
});
var chken = function(cp, i) {
var c = function(cp, i, e) {
var str = cptable.utils.encode(cp,i,e);
var arr = cptable.utils.encode(cp,i.split(""),e);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.encode(cp,Buffer_from(i),e);
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
cptable.utils.cache.decache();
c(cp,i);
c(cp,i,'buf');
c(cp,i,'arr');
c(cp,i,'str');
};
describe('encode', function() {
it('CP 1252 : sbcs', function() { chken(1252,"foo•bþr"); });
it('CP 708 : sbcs', function() { chken(708,"ت and ث smiley faces");});
it('CP 936 : dbcs', function() { chken(936, "这是中文字符测试");});
});
var chkde = function(cp, i) {
var c = function(cp, i) {
var s;
if(typeof Buffer !== 'undefined' && i instanceof Buffer) s = [].map.call(i, function(s){return String.fromCharCode(s); });
else s=(i.map) ? i.map(function(s){return String.fromCharCode(s); }) : i;
var str = cptable.utils.decode(cp,i);
var arr = cptable.utils.decode(cp,s.join?s.join(""):s);
assert.deepEqual(str,arr);
if(typeof Buffer === 'undefined') return;
var buf = cptable.utils.decode(cp,Buffer_from(i));
assert.deepEqual(str,buf);
};
cptable.utils.cache.encache();
c(cp,i);
cptable.utils.cache.decache();
c(cp,i);
};
describe('decode', function() {
it('CP 1252 : sbcs', function() { chkde(1252,[0x66, 0x6f, 0x6f, 0x62, 0x61, 0x72]); }); /* "foobar" */
if(typeof Buffer !== 'undefined') it('CP 708 : sbcs', function() { chkde(708, Buffer_from([0xca, 0x20, 0x61, 0x6e, 0x64, 0x20, 0xcb, 0x20, 0x73, 0x6d, 0x69, 0x6c, 0x65, 0x79, 0x20, 0x66, 0x61, 0x63, 0x65, 0x73])); }); /* ("ت and ث smiley faces") */
it('CP 936 : dbcs', function() { chkde(936, [0xd5, 0xe2, 0xca, 0xc7, 0xd6, 0xd0, 0xce, 0xc4, 0xd7, 0xd6, 0xb7, 0xfb, 0xb2, 0xe2, 0xca, 0xd4]);}); /* "这是中文字符测试" */
});
});
```
The `testfile` helper function reads a file and compares to node's read facilities:
```>test.js
function testfile(f,cp,type,skip) {
var d = fs.readFileSync(f);
var x = fs.readFileSync(f, type);
var a = x.split("");
var chk = function(cp) {
var y = cptable.utils.decode(cp, d);
assert.equal(x,y);
var z = cptable.utils.encode(cp, x);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(skip) return;
z = cptable.utils.encode(cp, a);
if(z.length != d.length) throw new Error(f + " " + JSON.stringify(z) + " != " + JSON.stringify(d) + " : " + z.length + " " + d.length);
for(var i = 0; i != d.length; ++i) if(d[i] !== z[i]) throw new Error("" + i + " " + d[i] + "!=" + z[i]);
if(f.indexOf("cptable.js") == -1) {
cptable.utils.encode(cp, d, 'str');
cptable.utils.encode(cp, d, 'arr');
}
}
cptable.utils.cache.encache();
chk(cp);
if(skip) return;
cptable.utils.cache.decache();
chk(cp);
cptable.utils.cache.encache();
}
```
The `utf8` tests verify UTF-8 encoding of the actual JS sources:
```>test.js
describe('node natives', function() {
var node = [[65001, 'utf8',1], [1200, 'utf16le',1], [20127, 'ascii',0]];
var unicodefiles = ['codepage.md','README.md','cptable.js'];
var asciifiles = ['cputils.js'];
node.forEach(function(w) {
describe(w[1], function() {
cptable = require('./');
asciifiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(!w[2]) return;
unicodefiles.forEach(function(f) {
it('should process ' + f, function() { testfile('./misc/'+f+'.'+w[1],w[0],w[1]); });
});
if(w[1] === 'utf8') it('should process bits', function() {
var files = fs.readdirSync('bits').filter(function(x){return x.substr(-3)==".js";});
files.forEach(function(f) { testfile('./bits/' + f,w[0],w[1],true); });
});
});
});
});
```
The `utf*` and `ascii` tests attempt to test other magic formats:
```>test.js
var m = cptable.utils.magic;
function cmp(x,z) {
assert.equal(x.length, z.length);
for(var i = 0; i != z.length; ++i) assert.equal(i+"/"+x.length+""+x[i], i+"/"+z.length+""+z[i]);
}
Object.keys(m).forEach(function(t){if(t != 16969) describe(m[t], function() {
it("should process codepage.md." + m[t], fs.existsSync('./misc/codepage.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/codepage.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/codepage.md.' + m[t]);
var y, z;
cptable.utils.cache.encache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.decache();
y = cptable.utils.decode(t, x);
assert.equal(y,b);
z = cptable.utils.encode(t, y);
if(t != 65000) cmp(x,z);
else { assert.equal(y, cptable.utils.decode(t, z)); }
cptable.utils.cache.encache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.decache();
cptable.utils.encode(t, y, 'str');
cptable.utils.encode(t, y, 'arr');
cptable.utils.cache.encache();
}
: null);
it("should process README.md." + m[t], fs.existsSync('./misc/README.md.' + m[t]) ?
function() {
var b = fs.readFileSync('./misc/README.md.utf8', "utf8");
if(m[t] === "ascii") b = b.replace(/[\u0080-\uffff]*/g,"");
var x = fs.readFileSync('./misc/README.md.' + m[t]);
x = [].slice.call(x);
cptable.utils.cache.encache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.decache();
var y = cptable.utils.decode(t, x);
assert.equal(y,b);
cptable.utils.cache.encache();
}
: null);
});});
```
The codepage `6969` is not defined, so operations should fail:
```>test.js
describe('failures', function() {
it('should fail to find CP 6969', function() {
assert.throws(function(){cptable[6969].dec});
assert.throws(function(){cptable[6969].enc});
});
it('should fail using utils', function() {
assert(!cptable.utils.hascp(6969));
assert.throws(function(){return cptable.utils.encode(6969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(6969, [0x20]); });
});
it('should fail with black magic', function() {
assert(cptable.utils.hascp(16969));
assert.throws(function(){return cptable.utils.encode(16969, "foobar"); });
assert.throws(function(){return cptable.utils.decode(16969, [0x20]); });
});
it('should fail when presented with invalid char codes', function() {
assert.throws(function(){cptable.utils.cache.decache(); return cptable.utils.encode(20127, [String.fromCharCode(0xAA)]);});
});
it('should fail to propagate UTF8 BOM in UTF7', function() {
["+/v8-abc", "+/v9"].forEach(function(m) { assert.throws(function() {
assert.equal(m, cptable.utils.encode(65000, cptable.utils.decode(65000, m)));
}); });
});
});
```
# Nitty Gritty
```json>package.json
{
"name": "codepage",
"version": "1.14.0",
"author": "SheetJS",
"description": "pure-JS library to handle codepages",
"keywords": [ "codepage", "iconv", "convert", "strings" ],
"bin": {
"codepage": "./bin/codepage.njs"
},
"main": "cputils.js",
"types": "types",
"browser": {
"buffer": "false"
},
"dependencies": {
"commander": "~2.14.1",
"exit-on-epipe": "~1.0.1"
},
"devDependencies": {
"voc": "~1.1.0",
"mocha": "~2.5.3",
"blanket": "~1.2.3",
"@sheetjs/uglify-js": "~2.7.3",
"@types/node": "^8.0.7",
"@types/commander": "^2.12.0",
"dtslint": "^0.1.2",
"typescript": "2.2.0"
},
"repository": { "type":"git", "url":"git://github.com/SheetJS/js-codepage.git"},
"scripts": {
"pretest": "git submodule init && git submodule update",
"test": "make test",
"build": "make js",
"lint": "make fullint",
"dtslint": "dtslint types"
},
"config": {
"blanket": {
"pattern": "[cputils.js]"
}
},
"alex": {
"allow": [
"chinese",
"european",
"german",
"japanese",
"latin"
]
},
"homepage": "http://sheetjs.com/opensource",
"files": [
"LICENSE",
"README.md",
"bin",
"bits/*.js",
"types/index.d.ts",
"types/*.json",
"cptable.js",
"cputils.js",
"dist/sbcs.full.js",
"dist/cpexcel.full.js"
],
"bugs": { "url": "https://github.com/SheetJS/js-codepage/issues" },
"license": "Apache-2.0",
"engines": { "node": ">=0.8" }
}
```
```>.vocrc
{ "post": "make js" }
```
```>.gitignore
node_modules
package-lock.json
*.tgz
.gitignore
codepages/
.vocrc
make.sh
make.njs
misc/coverage.html
codepage_mini.md
ctest/sauce*
```

View File

@ -2,16 +2,22 @@
The fields of the `pages.csv` manifest are `codepage,url,bytes` (SBCS=1, DBCS=2)
```>pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private `0xF8FF` code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the `ISO-8859-X` series is `28590 + X`:
## Generated Codepages
The following codepages are available in .NET on Windows:
- 708 Arabic (ASMO 708)
- 720 Arabic (Transparent ASMO); Arabic (DOS)
- 858 OEM Multilingual Latin 1 + Euro symbol
- 870 IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2
- 1047 IBM EBCDIC Latin 1/Open System
- 1140 IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro)
- 1141 IBM EBCDIC Germany (20273 + Euro sym

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -2,16 +2,22 @@
The fields of the +AGA-pages.csv+AGA manifest are +AGA-codepage,url,bytes+AGA (SBCS+AD0-1, DBCS+AD0-2)
+AGAAYABgAD4-pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private +AGA-0xF8FF+AGA code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the +AGA-ISO-8859-X+AGA series is +AGA-28590 +- X+AGA:
+ACMAIw Generated Codepages
The following codepages are available in .NET on Windows:
- 708 Arabic (ASMO 708)
- 720 Arabic (Transparent ASMO)+ADs Arabic (DOS)
- 858 OEM Multilingual Latin 1 +- Euro symbol
- 870 IBM EBCDIC Multilingual/ROECE (Latin 2)+ADs IBM EBCDIC Multilingual Latin 2
- 1047 IBM EBCDIC Latin 1/Open System
- 1140 IBM EBCDIC US-Canada (037 +- Euro symbol)+ADs IBM EBCDIC (US-Canada-Euro)
- 1141 IBM EBCDIC Germany (20273 +- Euro sym

View File

@ -2,16 +2,22 @@
The fields of the `pages.csv` manifest are `codepage,url,bytes` (SBCS=1, DBCS=2)
```>pages.csv
37,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT,1
437,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP437.TXT,1
500,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT,1
737,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP737.TXT,1
775,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP775.TXT,1
850,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP850.TXT,1
852,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP852.TXT,1
855,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP855.TXT,1
857,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP857.TXT,1
860,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP860.TXT,1
861,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP861.TXT,1
862,http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/CP862.TXT,1
Note that the Windows rendering is used for the Mac code pages. The primary
difference is the use of the private `0xF8FF` code (which renders as an Apple
logo on macs but as garbage on other operating systems). It may be desirable
to fall back to the behavior, in which case the files are under APPLE and not
MICSFT. This affects codepages 10000, 10006, 10007, 10029, 10079, 10081
The numbering scheme for the `ISO-8859-X` series is `28590 + X`:
## Generated Codepages
The following codepages are available in .NET on Windows:
- 708 Arabic (ASMO 708)
- 720 Arabic (Transparent ASMO); Arabic (DOS)
- 858 OEM Multilingual Latin 1 + Euro symbol
- 870 IBM EBCDIC Multilingual/ROECE (Latin 2); IBM EBCDIC Multilingual Latin 2
- 1047 IBM EBCDIC Latin 1/Open System
- 1140 IBM EBCDIC US-Canada (037 + Euro symbol); IBM EBCDIC (US-Canada-Euro)
- 1141 IBM EBCDIC Germany (20273 + Euro sym

File diff suppressed because it is too large Load Diff

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@ -1,4 +1,4 @@
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {
@ -40,11 +40,11 @@
var cca = function cca(x) { return x.charCodeAt(0); };
var has_buf = (typeof Buffer !== 'undefined');
var Buffer_from = function(){};
var Buffer_from = function(){};
if(has_buf) {
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
// $FlowIgnore
if(!Buffer.allocUnsafe) Buffer.allocUnsafe = function(n) { return new Buffer(n); };

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -1,4 +1,4 @@
/+ACo cputils.js (C) 2013-present SheetJS -- http://sheetjs.com +ACo-/
/+ACoAIQ cputils.js (C) 2013-present SheetJS -- http://sheetjs.com +ACo-/
/+ACo vim: set ft+AD0-javascript: +ACo-/
/+ACo-jshint newcap: false +ACo-/
(function(root, factory) +AHs
@ -40,11 +40,11 @@
var cca +AD0 function cca(x) +AHs return x.charCodeAt(0)+ADs +AH0AOw
var has+AF8-buf +AD0 (typeof Buffer +ACEAPQA9 'undefined')+ADs
var Buffer+AF8-from +AD0 function()+AHsAfQA7
var Buffer+AF8-from +AD0 function()+AHsAfQA7
if(has+AF8-buf) +AHs
var nbfs +AD0 +ACE-Buffer.from+ADs
if(+ACE-nbfs) try +AHs Buffer.from(+ACI-foo+ACI, +ACI-utf8+ACI)+ADs +AH0 catch(e) +AHs nbfs +AD0 true+ADs +AH0
Buffer+AF8-from +AD0 nbfs ? function(buf, enc) +AHs return (enc) ? new Buffer(buf, enc) : new Buffer(buf)+ADs +AH0 : Buffer.from.bind(Buffer)+ADs
var nbfs +AD0 +ACE-Buffer.from+ADs
if(+ACE-nbfs) try +AHs Buffer.from(+ACI-foo+ACI, +ACI-utf8+ACI)+ADs +AH0 catch(e) +AHs nbfs +AD0 true+ADs +AH0
Buffer+AF8-from +AD0 nbfs ? function(buf, enc) +AHs return (enc) ? new Buffer(buf, enc) : new Buffer(buf)+ADs +AH0 : Buffer.from.bind(Buffer)+ADs
// +ACQ-FlowIgnore
if(+ACE-Buffer.allocUnsafe) Buffer.allocUnsafe +AD0 function(n) +AHs return new Buffer(n)+ADs +AH0AOw

View File

@ -1,4 +1,4 @@
/* cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! cputils.js (C) 2013-present SheetJS -- http://sheetjs.com */
/* vim: set ft=javascript: */
/*jshint newcap: false */
(function(root, factory) {
@ -40,11 +40,11 @@
var cca = function cca(x) { return x.charCodeAt(0); };
var has_buf = (typeof Buffer !== 'undefined');
var Buffer_from = function(){};
var Buffer_from = function(){};
if(has_buf) {
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
var nbfs = !Buffer.from;
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
// $FlowIgnore
if(!Buffer.allocUnsafe) Buffer.allocUnsafe = function(n) { return new Buffer(n); };

View File

@ -1,6 +1,6 @@
{
"name": "codepage",
"version": "1.14.0",
"version": "1.15.0",
"author": "SheetJS",
"description": "pure-JS library to handle codepages",
"keywords": [
@ -49,7 +49,7 @@
"latin"
]
},
"homepage": "http://sheetjs.com/opensource",
"homepage": "https://sheetjs.com/",
"files": [
"LICENSE",
"README.md",

View File

@ -121,11 +121,6 @@
21866,,1
29001,,1
38598,,1
50220,,2
50221,,2
50222,,2
50225,,2
50227,,2
51932,,2
51936,,2
51949,,2

1 37 http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT 1
121 21866 1
122 29001 1
123 38598 1
50220 2
50221 2
50222 2
50225 2
50227 2
124 51932 2
125 51936 2
126 51949 2

View File

@ -1,6 +1,6 @@
/* sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*! sbcs.js (C) 2013-present SheetJS -- http://sheetjs.com */
/*jshint -W100 */
var cptable = {version:"1.14.0"};
var cptable = {version:"1.15.0"};
cptable[37] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ¢.<(+|&éêëèíîïìß!$*);¬-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®^£¥·©§¶¼½¾[]¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[437] = (function(){ var d = "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007\b\t\n\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~ÇüéâäàåçêëèïîìÄÅÉæÆôöòûùÿÖÜ¢£¥₧ƒáíóúñѪº¿⌐¬½¼¡«»░▒▓│┤╡╢╖╕╣║╗╝╜╛┐└┴┬├─┼╞╟╚╔╩╦╠═╬╧╨╤╥╙╘╒╓╫╪┘┌█▄▌▐▀αßΓπΣσµτΦΘΩδ∞φε∩≡±≥≤⌠⌡÷≈°∙·√ⁿ²■ ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();
cptable[500] = (function(){ var d = "\u0000\u0001\u0002\u0003œ\t†—Ž\u000b\f\r\u000e\u000f\u0010\u0011\u0012\u0013…\b‡\u0018\u0019’\u001c\u001d\u001e\u001f€‚ƒ„\n\u0017\u001bˆ‰Š‹Œ\u0005\u0006\u0007‘\u0016“”•–\u0004˜™š›\u0014\u0015ž\u001a  âäàáãåçñ[.<(+!&éêëèíîïìß]$*);^-/ÂÄÀÁÃÅÇѦ,%_>?øÉÊËÈÍÎÏÌ`:#@'=\"Øabcdefghi«»ðýþ±°jklmnopqrªºæ¸Æ¤µ~stuvwxyz¡¿ÐÝÞ®¢£¥·©§¶¼½¾¬|¯¨´×{ABCDEFGHI­ôöòóõ}JKLMNOPQR¹ûüùúÿ\\÷STUVWXYZ²ÔÖÒÓÕ0123456789³ÛÜÙڟ", D = [], e = {}; for(var i=0;i!=d.length;++i) { if(d.charCodeAt(i) !== 0xFFFD) e[d.charAt(i)] = i; D[i] = d.charAt(i); } return {"enc": e, "dec": D }; })();

View File

@ -1,5 +1,6 @@
var fs = require('fs'), assert = require('assert'), vm = require('vm');
var cptable, sbcs;
var Buffer_from = function(){};
if(typeof Buffer !== 'undefined') {
@ -7,6 +8,7 @@ if(typeof Buffer !== 'undefined') {
if(!nbfs) try { Buffer.from("foo", "utf8"); } catch(e) { nbfs = true; }
Buffer_from = nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer);
}
describe('source', function() {
it('should load node', function() { cptable = require('./'); });
it('should load sbcs', function() { sbcs = require('./sbcs'); });

View File

@ -9,6 +9,7 @@
"paths": { "codepage": ["."] },
"types": [],
"noEmit": true,
"strictFunctionTypes": true,
"forceConsistentCasingInFileNames": true
}
}