version bump 0.3.0

- AMD support (h/t @lmk123 for initially contributing to js-crc32)
- added missing bitshift (h/t @florentbr for initially contributing to js-crc32)
- flow annotaations
- updated ci node versions

.flowconfig

@@ -0,0 +1,17 @@
+[ignore]
+.*/node_modules/.*
+.*/dist/.*
+.*/test.js
+.*/adler32.js
+
+.*/bits/.*
+.*/ctest/.*
+.*/misc/.*
+.*/perf/.*
+
+[include]
+adler32.flow.js
+
+[libs]
+
+[options]

.gitignore

@@ -1,3 +1,6 @@
 node_modules
+test_files/*.py
+test_files/*.js
+test_files/baseline*
 misc/coverage.html
 misc/*/

.jshintrc

@@ -0,0 +1,5 @@
+{
+	"bitwise": false,
+	"curly": false
+}
+

.npmignore

@@ -0,0 +1,14 @@
+node_modules
+misc/
+perf/
+bits/
+ctest/
+test_files/
+test.js
+.travis.yml
+.jscs.json
+.jshintrc
+.flowconfig
+.npmignore
+perf.txt
+Makefile

.travis.yml

@@ -1,10 +1,14 @@
 language: node_js
 node_js:
-  - "0.11"
+  - "5.0"
+  - "4.2"
+  - "0.12"
   - "0.10"
   - "0.8"
 before_install:
+  - "npm install -g npm@next"
   - "npm install -g mocha"
+  - "npm install codepage"
   - "npm install blanket"
   - "npm install coveralls mocha-lcov-reporter"
 after_success:

LICENSE

@@ -1,4 +1,4 @@
-Copyright (C) 2014  SheetJS
+Copyright (C) 2014-present  SheetJS
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

Makefile

@@ -1,32 +1,47 @@
 LIB=adler32
+REQS=
+ADDONS=
+AUXTARGETS=
+
+ULIB=$(shell echo $(LIB) | tr a-z A-Z)
 DEPS=$(sort $(wildcard bits/*.js))
 TARGET=$(LIB).js
 
-$(TARGET): $(DEPS)
+.PHONY: all
+all: $(TARGET) $(AUXTARGETS)
+
+$(TARGET) $(AUXTARGETS): %.js : %.flow.js
+	node -e 'process.stdout.write(require("fs").readFileSync("$<","utf8").replace(/^\s*\/\*:[^*]*\*\/\s*(\n)?/gm,"").replace(/\/\*:[^*]*\*\//gm,""))' > $@
+
+$(LIB).flow.js: $(DEPS)
 	cat $^ | tr -d '\15\32' > $@
-	cp -f $@ ctest/ 
 
 bits/01_version.js: package.json
 	echo "ADLER32.version = '"`grep version package.json | awk '{gsub(/[^0-9a-z\.-]/,"",$$2); print $$2}'`"';" > $@
 
 .PHONY: clean
-clean:
+clean: clean-baseline
 	rm -f $(TARGET)
 
 .PHONY: test mocha
-test mocha: test.js
-	mocha -R spec
+test mocha: test.js $(TARGET) baseline
+	mocha -R spec -t 20000
 
 .PHONY: ctest
 ctest:
 	cat misc/*.js > ctest/fixtures.js
 	cp -f test.js ctest/test.js
-	cp -f $(TARGET) ctest/ 
+	cp -f $(TARGET) ctest/
 
 .PHONY: lint
-lint: $(TARGET)
-	jshint --show-non-errors $(TARGET)
-	jscs $(TARGET)
+lint: $(TARGET) $(AUXTARGETS)
+	jshint --show-non-errors $(TARGET) $(AUXTARGETS)
+	jshint --show-non-errors package.json
+	jscs $(TARGET) $(AUXTARGETS)
+
+.PHONY: flow
+flow: lint
+	flow check --all --show-all-errors
 
 .PHONY: cov cov-spin
 cov: misc/coverage.html
@@ -39,11 +54,11 @@ $(COVFMT): cov_%:
 	FMTS=$* make cov
 
 misc/coverage.html: $(TARGET) test.js
-	mocha --require blanket -R html-cov > $@
+	mocha --require blanket -R html-cov -t 20000 > $@
 
 .PHONY: coveralls coveralls-spin
 coveralls:
-	mocha --require blanket --reporter mocha-lcov-reporter | ./node_modules/coveralls/bin/coveralls.js
+	mocha --require blanket --reporter mocha-lcov-reporter -t 20000 | ./node_modules/coveralls/bin/coveralls.js
 
 coveralls-spin:
 	make coveralls & bash misc/spin.sh $$!
@@ -51,3 +66,14 @@ coveralls-spin:
 .PHONY: perf
 perf:
 	bash perf/perf.sh
+
+.PHONY: perf-all
+perf-all:
+	bash misc/perf.sh
+
+.PHONY: baseline clean-baseline
+baseline:
+	./misc/make_baseline.sh
+
+clean-baseline:
+	rm -f test_files/*.*

README.md

@@ -79,9 +79,11 @@ Subtract up to 4 elements for the unicode case.
 Please consult the attached LICENSE file for details.  All rights not explicitly
 granted by the Apache 2.0 license are reserved by the Original Author.
 
+## Badges
+
 [![Build Status](https://travis-ci.org/SheetJS/js-adler32.svg?branch=master)](https://travis-ci.org/SheetJS/js-adler32)
 
 [![Coverage Status](https://coveralls.io/repos/SheetJS/js-adler32/badge.png?branch=master)](https://coveralls.io/r/SheetJS/js-adler32?branch=master)
 
-[![githalytics.com alpha](https://cruel-carlota.pagodabox.com/8827aa40b3fdbca7c7ad0f51c68b3379 "githalytics.com")](http://githalytics.com/SheetJS/js-adler32)
+[![Analytics](https://ga-beacon.appspot.com/UA-36810333-1/SheetJS/js-adler32?pixel)](https://github.com/SheetJS/js-adler32)
 

adler32.flow.js

@@ -0,0 +1,91 @@
+/* adler32.js (C) 2014-present SheetJS -- http://sheetjs.com */
+/* vim: set ts=2: */
+var ADLER32;
+/*:: declare var DO_NOT_EXPORT_ADLER: any; */
+/*:: declare var define: any; */
+(function (factory) {
+	if(typeof DO_NOT_EXPORT_ADLER === 'undefined') {
+		if('object' === typeof exports) {
+			factory(exports);
+		} else if ('function' === typeof define && define.amd) {
+			define(function () {
+				var module = {};
+				factory(module);
+				return module;
+			});
+		} else {
+			factory(ADLER32 = {});
+		}
+	} else {
+		factory(ADLER32 = {});
+	}
+}(function(ADLER32) {
+ADLER32.version = '0.3.0';
+/*::
+type ADLER32Type = number;
+type ABuf = Array<number> | Buffer;
+*/
+/* consult README.md for the magic number */
+/* charCodeAt is the best approach for binary strings */
+var use_buffer = typeof Buffer !== 'undefined';
+function adler32_bstr(bstr/*:string*/)/*:ADLER32Type*/ {
+	if(bstr.length > 32768) if(use_buffer) return adler32_buf(new Buffer(bstr));
+	var a = 1, b = 0, L = bstr.length, M;
+	for(var i = 0; i < L;) {
+		M = Math.min(L-i, 3850)+i;
+		for(;i<M;i++) {
+			a += bstr.charCodeAt(i);
+			b += a;
+		}
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
+	}
+	return ((b%65521) << 16) | (a%65521);
+}
+
+function adler32_buf(buf/*:ABuf*/)/*:ADLER32Type*/ {
+	var a = 1, b = 0, L = buf.length, M;
+	for(var i = 0; i < L;) {
+		M = Math.min(L-i, 3850)+i;
+		for(;i<M;i++) {
+			a += buf[i];
+			b += a;
+		}
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
+	}
+	return ((b%65521) << 16) | (a%65521);
+}
+
+/* much much faster to intertwine utf8 and adler */
+function adler32_str(str/*:string*/)/*:ADLER32Type*/ {
+	var a = 1, b = 0, L = str.length, M, c, d;
+	for(var i = 0; i < L;) {
+		M = Math.min(L-i, 3850);
+		while(M>0) {
+			c = str.charCodeAt(i++);
+			if(c < 0x80) { a += c; b += a; --M; }
+			else if(c < 0x800) {
+				a += 192|((c>>6)&31);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
+			} else if(c >= 0xD800 && c < 0xE000) {
+				c = (c&1023)+64; d = str.charCodeAt(i++) & 1023;
+				a += 240|((c>>8)&7);              b += a; --M;
+				a += 128|((c>>2)&63);             b += a; --M;
+				a += 128|((d>>6)&15)|((c&3)<<4);  b += a; --M;
+				a += 128|(d&63);                  b += a; --M;
+			} else {
+				a += 224|((c>>12)&15);            b += a; --M;
+				a += 128|((c>>6)&63);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
+			}
+		}
+		a %= 65521;
+		b %= 65521;
+	}
+	return (b << 16) | a;
+}
+ADLER32.bstr = adler32_bstr;
+ADLER32.buf = adler32_buf;
+ADLER32.str = adler32_str;
+}));

adler32.js

@@ -1,13 +1,29 @@
-/* adler32.js (C) 2014 SheetJS -- http://sheetjs.com */
+/* adler32.js (C) 2014-present SheetJS -- http://sheetjs.com */
 /* vim: set ts=2: */
-var ADLER32 = {};
-(function(ADLER32) {
-ADLER32.version = '0.2.0';
+var ADLER32;
+(function (factory) {
+	if(typeof DO_NOT_EXPORT_ADLER === 'undefined') {
+		if('object' === typeof exports) {
+			factory(exports);
+		} else if ('function' === typeof define && define.amd) {
+			define(function () {
+				var module = {};
+				factory(module);
+				return module;
+			});
+		} else {
+			factory(ADLER32 = {});
+		}
+	} else {
+		factory(ADLER32 = {});
+	}
+}(function(ADLER32) {
+ADLER32.version = '0.3.0';
 /* consult README.md for the magic number */
 /* charCodeAt is the best approach for binary strings */
 var use_buffer = typeof Buffer !== 'undefined';
 function adler32_bstr(bstr) {
-	if(bstr.length > 32768) if(use_buffer) return adler32_buf(Buffer(bstr));
+	if(bstr.length > 32768) if(use_buffer) return adler32_buf(new Buffer(bstr));
 	var a = 1, b = 0, L = bstr.length, M;
 	for(var i = 0; i < L;) {
 		M = Math.min(L-i, 3850)+i;
@@ -15,8 +31,8 @@ function adler32_bstr(bstr) {
 			a += bstr.charCodeAt(i);
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
@@ -29,8 +45,8 @@ function adler32_buf(buf) {
 			a += buf[i];
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
@@ -44,18 +60,18 @@ function adler32_str(str) {
 			c = str.charCodeAt(i++);
 			if(c < 0x80) { a += c; b += a; --M; }
 			else if(c < 0x800) {
-				a += 192|((c>>6)&31);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 192|((c>>6)&31);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			} else if(c >= 0xD800 && c < 0xE000) {
 				c = (c&1023)+64; d = str.charCodeAt(i++) & 1023;
-				a += 240|((c>>8)&7);         b += a; --M;
-				a += 128|((c>>2)&63);        b += a; --M;
-				a += 128|((d>>6)&15)|(c&3);  b += a; --M;
-				a += 128|(d&63);             b += a; --M;
+				a += 240|((c>>8)&7);              b += a; --M;
+				a += 128|((c>>2)&63);             b += a; --M;
+				a += 128|((d>>6)&15)|((c&3)<<4);  b += a; --M;
+				a += 128|(d&63);                  b += a; --M;
 			} else {
-				a += 224|((c>>12)&15);       b += a; --M;
-				a += 128|((c>>6)&63);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 224|((c>>12)&15);            b += a; --M;
+				a += 128|((c>>6)&63);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			}
 		}
 		a %= 65521;
@@ -66,4 +82,4 @@ function adler32_str(str) {
 ADLER32.bstr = adler32_bstr;
 ADLER32.buf = adler32_buf;
 ADLER32.str = adler32_str;
-})(typeof exports !== "undefined" && typeof DO_NOT_EXPORT_ADLER === 'undefined' ? exports : ADLER32);
+}));

bits/00_header.js

@@ -1,4 +1,22 @@
-/* adler32.js (C) 2014 SheetJS -- http://sheetjs.com */
+/* adler32.js (C) 2014-present SheetJS -- http://sheetjs.com */
 /* vim: set ts=2: */
-var ADLER32 = {};
-(function(ADLER32) {
+var ADLER32;
+/*:: declare var DO_NOT_EXPORT_ADLER: any; */
+/*:: declare var define: any; */
+(function (factory) {
+	if(typeof DO_NOT_EXPORT_ADLER === 'undefined') {
+		if('object' === typeof exports) {
+			factory(exports);
+		} else if ('function' === typeof define && define.amd) {
+			define(function () {
+				var module = {};
+				factory(module);
+				return module;
+			});
+		} else {
+			factory(ADLER32 = {});
+		}
+	} else {
+		factory(ADLER32 = {});
+	}
+}(function(ADLER32) {

bits/01_version.js

@@ -1 +1 @@
-ADLER32.version = '0.2.0';
+ADLER32.version = '0.3.0';

bits/10_types.js

@@ -0,0 +1,4 @@
+/*::
+type ADLER32Type = number;
+type ABuf = Array<number> | Buffer;
+*/

bits/40_adler.js

@@ -1,8 +1,8 @@
 /* consult README.md for the magic number */
 /* charCodeAt is the best approach for binary strings */
 var use_buffer = typeof Buffer !== 'undefined';
-function adler32_bstr(bstr) {
-	if(bstr.length > 32768) if(use_buffer) return adler32_buf(Buffer(bstr));
+function adler32_bstr(bstr/*:string*/)/*:ADLER32Type*/ {
+	if(bstr.length > 32768) if(use_buffer) return adler32_buf(new Buffer(bstr));
 	var a = 1, b = 0, L = bstr.length, M;
 	for(var i = 0; i < L;) {
 		M = Math.min(L-i, 3850)+i;
@@ -10,13 +10,13 @@ function adler32_bstr(bstr) {
 			a += bstr.charCodeAt(i);
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
 
-function adler32_buf(buf) {
+function adler32_buf(buf/*:ABuf*/)/*:ADLER32Type*/ {
 	var a = 1, b = 0, L = buf.length, M;
 	for(var i = 0; i < L;) {
 		M = Math.min(L-i, 3850)+i;
@@ -24,14 +24,14 @@ function adler32_buf(buf) {
 			a += buf[i];
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
 
 /* much much faster to intertwine utf8 and adler */
-function adler32_str(str) {
+function adler32_str(str/*:string*/)/*:ADLER32Type*/ {
 	var a = 1, b = 0, L = str.length, M, c, d;
 	for(var i = 0; i < L;) {
 		M = Math.min(L-i, 3850);
@@ -39,18 +39,18 @@ function adler32_str(str) {
 			c = str.charCodeAt(i++);
 			if(c < 0x80) { a += c; b += a; --M; }
 			else if(c < 0x800) {
-				a += 192|((c>>6)&31);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 192|((c>>6)&31);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			} else if(c >= 0xD800 && c < 0xE000) {
 				c = (c&1023)+64; d = str.charCodeAt(i++) & 1023;
-				a += 240|((c>>8)&7);         b += a; --M;
-				a += 128|((c>>2)&63);        b += a; --M;
-				a += 128|((d>>6)&15)|(c&3);  b += a; --M;
-				a += 128|(d&63);             b += a; --M;
+				a += 240|((c>>8)&7);              b += a; --M;
+				a += 128|((c>>2)&63);             b += a; --M;
+				a += 128|((d>>6)&15)|((c&3)<<4);  b += a; --M;
+				a += 128|(d&63);                  b += a; --M;
 			} else {
-				a += 224|((c>>12)&15);       b += a; --M;
-				a += 128|((c>>6)&63);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 224|((c>>12)&15);            b += a; --M;
+				a += 128|((c>>6)&63);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			}
 		}
 		a %= 65521;

bits/99_footer.js

@@ -1 +1 @@
-})(typeof exports !== "undefined" && typeof DO_NOT_EXPORT_ADLER === 'undefined' ? exports : ADLER32);
+}));

ctest/adler32.js

@@ -1,13 +1,29 @@
-/* adler32.js (C) 2014 SheetJS -- http://sheetjs.com */
+/* adler32.js (C) 2014-present SheetJS -- http://sheetjs.com */
 /* vim: set ts=2: */
-var ADLER32 = {};
-(function(ADLER32) {
-ADLER32.version = '0.2.0';
+var ADLER32;
+(function (factory) {
+	if(typeof DO_NOT_EXPORT_ADLER === 'undefined') {
+		if('object' === typeof exports) {
+			factory(exports);
+		} else if ('function' === typeof define && define.amd) {
+			define(function () {
+				var module = {};
+				factory(module);
+				return module;
+			});
+		} else {
+			factory(ADLER32 = {});
+		}
+	} else {
+		factory(ADLER32 = {});
+	}
+}(function(ADLER32) {
+ADLER32.version = '0.3.0';
 /* consult README.md for the magic number */
 /* charCodeAt is the best approach for binary strings */
 var use_buffer = typeof Buffer !== 'undefined';
 function adler32_bstr(bstr) {
-	if(bstr.length > 32768) if(use_buffer) return adler32_buf(Buffer(bstr));
+	if(bstr.length > 32768) if(use_buffer) return adler32_buf(new Buffer(bstr));
 	var a = 1, b = 0, L = bstr.length, M;
 	for(var i = 0; i < L;) {
 		M = Math.min(L-i, 3850)+i;
@@ -15,8 +31,8 @@ function adler32_bstr(bstr) {
 			a += bstr.charCodeAt(i);
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
@@ -29,8 +45,8 @@ function adler32_buf(buf) {
 			a += buf[i];
 			b += a;
 		}
-		a = (15*(a>>>16)+(a&65535))
-		b = (15*(b>>>16)+(b&65535))
+		a = (15*(a>>>16)+(a&65535));
+		b = (15*(b>>>16)+(b&65535));
 	}
 	return ((b%65521) << 16) | (a%65521);
 }
@@ -44,18 +60,18 @@ function adler32_str(str) {
 			c = str.charCodeAt(i++);
 			if(c < 0x80) { a += c; b += a; --M; }
 			else if(c < 0x800) {
-				a += 192|((c>>6)&31);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 192|((c>>6)&31);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			} else if(c >= 0xD800 && c < 0xE000) {
 				c = (c&1023)+64; d = str.charCodeAt(i++) & 1023;
-				a += 240|((c>>8)&7);         b += a; --M;
-				a += 128|((c>>2)&63);        b += a; --M;
-				a += 128|((d>>6)&15)|(c&3);  b += a; --M;
-				a += 128|(d&63);             b += a; --M;
+				a += 240|((c>>8)&7);              b += a; --M;
+				a += 128|((c>>2)&63);             b += a; --M;
+				a += 128|((d>>6)&15)|((c&3)<<4);  b += a; --M;
+				a += 128|(d&63);                  b += a; --M;
 			} else {
-				a += 224|((c>>12)&15);       b += a; --M;
-				a += 128|((c>>6)&63);        b += a; --M;
-				a += 128|(c&63);             b += a; --M;
+				a += 224|((c>>12)&15);            b += a; --M;
+				a += 128|((c>>6)&63);             b += a; --M;
+				a += 128|(c&63);                  b += a; --M;
 			}
 		}
 		a %= 65521;
@@ -66,4 +82,4 @@ function adler32_str(str) {
 ADLER32.bstr = adler32_bstr;
 ADLER32.buf = adler32_buf;
 ADLER32.str = adler32_str;
-})(typeof exports !== "undefined" && typeof DO_NOT_EXPORT_ADLER === 'undefined' ? exports : ADLER32);
+}));

ctest/test.js

@@ -4,13 +4,16 @@ if(typeof require !== 'undefined') {
 	assert = require('assert');
 	describe('source',function(){it('should load',function(){X=require('./');});});
 	bits = require('./misc/bits.js');
+	fs = require("fs");
 } else { X = ADLER32; }
 
+function readlines(f) { return fs.readFileSync(f, "ascii").split("\n").filter(function(f) { return !!f; }); }
+
 describe('adler32 bits', function() {
 	bits.forEach(function(i) {
 		var l = i[0].length;
 		var msg = i[0];
-		if(l > 20) i[0].substr(0,5) + "...(" + l + ")..." + i[0].substr(-5);
+		if(l > 20) msg = i[0].substr(0,5) + "...(" + l + ")..." + i[0].substr(-5);
 		it(msg, function() {
 			if(i[2] === 1) assert.equal(X.bstr(i[0]), i[1]|0);
 			assert.equal(X.str(i[0]), i[1]|0);
@@ -18,4 +21,20 @@ describe('adler32 bits', function() {
 		});
 	});
 });
-
+if(typeof require !== 'undefined') describe("unicode", function() {
+	if(!fs.existsSync("./test_files/uccat.txt")) return;
+	var uccat = readlines("./test_files/uccat.txt");
+	uccat.forEach(function(cat) {
+		it("Category " + cat, function() {
+			if(!fs.existsSync("./test_files/baseline." + cat + ".txt")) return;
+			var corpus = readlines("./test_files/baseline." + cat + ".txt");
+			var uctable = require("./test_files/uctable." + cat + ".js");
+			uctable.forEach(function(c, i) {
+				/* since the baselines are passed via utf8, discard invalid codes */
+				if(c.charCodeAt(0) >= 0xD800 && c.charCodeAt(0) < 0xE000) return;
+				var cc = corpus[i], dd = X.str(c);
+				assert.equal(dd, cc, ":" + i + ":" + c + ":" + cc + ":" + dd);
+			});
+		});
+	});
+});

misc/make_baseline.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+# make_baseline.sh -- generate baselines for tests
+# Copyright (C) 2016-present  SheetJS
+OUTD=../test_files
+CATURL=https://mathias.html5.org/data/unicode/8.0.0/categories/
+CATF=$OUTD/uccat.txt
+
+ECHORED() { echo -ne '\x1B[0;31m'; echo -n $1; echo -ne '\x1B[0m'; echo; }
+
+if [ -d misc ]; then cd misc; fi
+mkdir -p $OUTD
+if [ ! -e $CATF ]; then curl "$CATURL" | grep "code-points" | sed 's/.*="//g;s/-.*//g' > $CATF; fi
+
+while read line; do
+	JSF=uctable.${line}.js
+	PYF=uctable_${line}.py
+	BLF=baseline.${line}.txt
+	JSURL="https://mathias.html5.org/data/unicode/format?version=8.0.0&category=${line}&type=symbols&prepend=var+unicode%20%3D%20&append=%3Bif(typeof%20module%20!%3D%3D%20'undefined')%20module.exports%20%3D%20unicode%3B"
+	if [[ ! -e $OUTD/$JSF || ! -e $OUTD/$PYF || ! -e $OUTD/$BLF ]]; then
+		ECHORED "Processing ${line}"
+		if [ ! -e $JSF ]; then
+			rm -f $PYF $BLF ${PYF}c
+			echo "Downloading JS"
+			</dev/null curl -o $JSF "$JSURL"
+		fi
+		if [ ! -e $PYF ]; then
+			echo "Building Python script"
+			rm -f $BLF ${PYF}c
+			</dev/null node make_unicode.njs ${line} | sed 's/\[ \[/uctable = \[ \[/' > $PYF
+		fi
+		if [ ! -e $BLF ]; then
+			echo "Building Baseline text"
+			python make_unicode_adler.py ${line} > baseline.${line}.txt
+		fi
+		for i in $JSF $PYF $BLF; do if [ -e $i ]; then mv $i $OUTD/; fi; done
+		rm -f uctable_${line}.pyc
+	fi
+done < $CATF
+

misc/make_unicode.njs

@@ -0,0 +1,5 @@
+#!/usr/bin/env node
+argv = process.argv.slice(2);
+var enc = require('codepage').utils.encode;
+function arr(x) { return [].slice.call(enc(65001, x)); }
+console.log(require('./uctable.' + argv[0]).map(arr));

misc/make_unicode_adler.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+# make_unicode_crc.py -- generate baselines for tests
+# Copyright (C) 2016-present  SheetJS
+
+from zlib import adler32 
+from array import array
+from sys import argv, stderr, exit
+from importlib import import_module
+
+args = argv[1:]
+
+if len(args) < 1:
+	print >>stderr, "usage: " + argv[0] + " <category>"
+	exit(1)
+
+uctable = import_module("uctable_" + args[0]).uctable
+
+for z in uctable:
+	print adler32(array('B', z));

misc/spin.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 # spin.sh -- show a spinner (for coverage test)
-# Copyright (C) 2014  SheetJS
+# Copyright (C) 2014-present  SheetJS
 
 wpid=$1
 delay=1

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "adler-32",
-	"version": "0.2.1",
+	"version": "0.3.0",
 	"author": "sheetjs",
 	"description": "Pure-JS ADLER-32",
 	"keywords": [ "adler32", "checksum" ],

test.js

@@ -4,13 +4,16 @@ if(typeof require !== 'undefined') {
 	assert = require('assert');
 	describe('source',function(){it('should load',function(){X=require('./');});});
 	bits = require('./misc/bits.js');
+	fs = require("fs");
 } else { X = ADLER32; }
 
+function readlines(f) { return fs.readFileSync(f, "ascii").split("\n").filter(function(f) { return !!f; }); }
+
 describe('adler32 bits', function() {
 	bits.forEach(function(i) {
 		var l = i[0].length;
 		var msg = i[0];
-		if(l > 20) i[0].substr(0,5) + "...(" + l + ")..." + i[0].substr(-5);
+		if(l > 20) msg = i[0].substr(0,5) + "...(" + l + ")..." + i[0].substr(-5);
 		it(msg, function() {
 			if(i[2] === 1) assert.equal(X.bstr(i[0]), i[1]|0);
 			assert.equal(X.str(i[0]), i[1]|0);
@@ -18,4 +21,20 @@ describe('adler32 bits', function() {
 		});
 	});
 });
-
+if(typeof require !== 'undefined') describe("unicode", function() {
+	if(!fs.existsSync("./test_files/uccat.txt")) return;
+	var uccat = readlines("./test_files/uccat.txt");
+	uccat.forEach(function(cat) {
+		it("Category " + cat, function() {
+			if(!fs.existsSync("./test_files/baseline." + cat + ".txt")) return;
+			var corpus = readlines("./test_files/baseline." + cat + ".txt");
+			var uctable = require("./test_files/uctable." + cat + ".js");
+			uctable.forEach(function(c, i) {
+				/* since the baselines are passed via utf8, discard invalid codes */
+				if(c.charCodeAt(0) >= 0xD800 && c.charCodeAt(0) < 0xE000) return;
+				var cc = corpus[i], dd = X.str(c);
+				assert.equal(dd, cc, ":" + i + ":" + c + ":" + cc + ":" + dd);
+			});
+		});
+	});
+});

test_files/uccat.txt

@@ -0,0 +1,38 @@
+C
+Cc
+Cf
+Cn
+Co
+Cs
+L
+LC
+Ll
+Lm
+Lo
+Lt
+Lu
+M
+Mc
+Me
+Mn
+N
+Nd
+Nl
+No
+P
+Pc
+Pd
+Pe
+Pf
+Pi
+Po
+Ps
+S
+Sc
+Sk
+Sm
+So
+Z
+Zl
+Zp
+Zs