This commit is contained in:
SheetJS 2023-05-20 22:11:51 -04:00
parent b6095aff3f
commit 8000cfcbd7
8 changed files with 369 additions and 2 deletions

2
.gitignore vendored

@ -2,4 +2,4 @@
*.bak
package-lock.json
pnpm-lock.yaml
docs
/docs

@ -13,7 +13,7 @@ init:
.PHONY: dev
dev:
cd docz; npm run start; cd ..
cd docz; npm run start -- --host=0.0.0.0; cd ..
.PHONY: serve
serve:

@ -0,0 +1,261 @@
---
title: C++ + V8
pagination_prev: demos/bigdata/index
pagination_next: solutions/input
---
import current from '/version.js';
import CodeBlock from '@theme/CodeBlock';
V8 is an embeddable JS engine written in C++. It powers Chromium and Chrome,
NodeJS and Deno, Adobe UXP and other platforms.
The [Standalone scripts](/docs/getting-started/installation/standalone) can be
parsed and evaluated in a V8 context.
## Integration Details
_Initialize V8_
The official V8 `hello-world` example covers initialization and cleanup. For the
purposes of this demo, the key variables are noted below:
```cpp
v8::Isolate* isolate = v8::Isolate::New(create_params);
v8::Local<v8::Context> context = v8::Context::New(isolate);
```
The following helper function evaluates C strings as JS code:
```cpp
v8::Local<v8::Value> eval_code(v8::Isolate *i, v8::Local<v8::Context> c, char* code) {
v8::Local<v8::String> source = v8::String::NewFromUtf8(i, code).ToLocalChecked();
v8::Local<v8::Script> script = v8::Script::Compile(i, source).ToLocalChecked();
return script->Run(c).ToLocalChecked();
}
```
_Load SheetJS Scripts_
The main library can be loaded by reading the scripts from the file system and
evaluating in the V8 context:
```cpp
/* simple wrapper to read the entire script file */
static char *read_file(const char *filename, size_t *sz) {
FILE *f = fopen(filename, "rb");
if(!f) return NULL;
long fsize; { fseek(f, 0, SEEK_END); fsize = ftell(f); fseek(f, 0, SEEK_SET); }
char *buf = (char *)malloc(fsize * sizeof(char));
*sz = fread((void *) buf, 1, fsize, f);
fclose(f);
return buf;
}
// ...
size_t sz; char *file = read_file("xlsx.full.min.js", &sz);
v8::Local<v8::Value> result = eval_code(isolate, context, file);
```
To confirm the library is loaded, `XLSX.version` can be inspected:
```cpp
/* get version string */
v8::Local<v8::Value> result = eval_code(isolate, context, "XLSX.version");
v8::String::Utf8Value vers(isolate, result);
printf("SheetJS library version %s\n", *vers);
```
### Reading Files
V8 supports `ArrayBuffer` natively. Assuming `buf` is a C byte array, with
length `len`, this snippet stores the data as an `ArrayBuffer` in global scope:
```cpp
/* load C char array and save to an ArrayBuffer */
std::unique_ptr<v8::BackingStore> back = v8::ArrayBuffer::NewBackingStore(isolate, len);
memcpy(back->Data(), buf, len);
v8::Local<v8::ArrayBuffer> ab = v8::ArrayBuffer::New(isolate, std::move(back));
v8::Maybe<bool> res = context->Global()->Set(context, v8::String::NewFromUtf8Literal(isolate, "buf"), ab);
/* parse with SheetJS */
v8::Local<v8::Value> result = eval_code(isolate, context, "globalThis.wb = XLSX.read(buf)");
```
`wb` will be a variable in the JS environment that can be inspected using the
various SheetJS API functions.
### Writing Files
The underlying memory from an `ArrayBuffer` can be recovered:
```c
/* write with SheetJS using type: "array" */
v8::Local<v8::Value> result = eval_code(isolate, context, "XLSX.write(wb, {type:'array', bookType:'xlsb'})");
/* pull result back to C++ */
v8::Local<v8::ArrayBuffer> ab = v8::Local<v8::ArrayBuffer>::Cast(result);
size_t sz = ab->ByteLength();
char *buf = ab->Data();
```
The resulting `buf` can be written to file with `fwrite`.
## Complete Example
:::note
This demo was tested in the following deployments:
| V8 Version | Platform | OS Version | Compiler | Date |
|:--------------|:-------------|:-----------|:---------------|:-----------|
| `11.3.244.11` | `darwin-x64` | macOS 13.2 | `clang 14.0.3` | 2023-05-20 |
:::
This program parses a file and prints CSV data from the first worksheet. It also
generates an XLSB file and writes to the filesystem.
:::caution
At the time of writing, there were errors in the official V8 embed guide for the
macOS platform. The correct instructions are included below.
:::
:::caution
The build process is long and will test your patience.
:::
### Preparation
1) Download and install `depot_tools`:
```bash
mkdir -p /usr/local/lib
cd /usr/local/lib
git clone https://chromium.googlesource.com/chromium/tools/depot_tools.git
```
2) Add the path to the `PATH` environment variable:
```bash
export PATH="/usr/local/lib/depot_tools:$PATH"
```
At this point, it is strongly recommended to add the line to a shell startup
script such as `.bashrc` or `.zshrc`
3) Run `gclient` once to update `depot_tools`:
```bash
gclient
```
### Clone V8
4) Create a base directory:
```bash
mkdir -p ~/dev/v8
cd ~/dev/v8
fetch v8
cd v8
```
Note that the actual repo will be placed in `~/dev/v8/v8`.
5) Checkout the desired version. The following command pulls `11.3.244.11`:
```bash
git checkout refs/tags/11.3.244.11 -b sample -t
```
### Build V8
6) Build the static library.
```bash
tools/dev/v8gen.py x64.release.sample
ninja -C out.gn/x64.release.sample v8_monolith
```
7) Ensure the sample `hello-world` compiles and runs:
```bash
g++ -I. -Iinclude samples/hello-world.cc -o hello_world -fno-rtti -lv8_monolith \
-lv8_libbase -lv8_libplatform -ldl -Lout.gn/x64.release.sample/obj/ -pthread \
-std=c++17 -DV8_COMPRESS_POINTERS=1 -DV8_ENABLE_SANDBOX
./hello_world
```
### Prepare Project
8) Make a new project folder:
```bash
cd ~/dev
mkdir sheetjs-v8
cd sheetjs-v8
```
9) Copy the sample source:
```bash
cp ~/dev/v8/v8/samples/hello-world.cc .
```
10) Create symbolic links to the `include` headers and `obj` library folders:
```bash
ln -s ~/dev/v8/v8/include
ln -s ~/dev/v8/v8/out.gn/x64.release.sample/obj
```
11) Build and run the `hello-world` example from this folder:
```bash
g++ -I. -Iinclude hello-world.cc -o hello_world -fno-rtti -lv8_monolith \
-lv8_libbase -lv8_libplatform -ldl -Lobj/ -pthread -std=c++17 \
-DV8_COMPRESS_POINTERS=1 -DV8_ENABLE_SANDBOX
./hello_world
```
### Add SheetJS
12) Download the standalone script and test file:
<ul>
<li><a href={`https://cdn.sheetjs.com/xlsx-${current}/package/dist/xlsx.full.min.js`}>xlsx.full.min.js</a></li>
<li><a href="https://sheetjs.com/pres.numbers">pres.numbers</a></li>
</ul>
<CodeBlock language="bash">{`\
curl -LO https://cdn.sheetjs.com/xlsx-${current}/package/dist/xlsx.full.min.js
curl -LO https://sheetjs.com/pres.numbers`}
</CodeBlock>
13) Download [`sheetjs.v8.cc`](pathname:///v8/sheetjs.v8.cc):
```bash
curl -LO https://docs.sheetjs.com/v8/sheetjs.v8.cc
```
14) Compile standalone `sheetjs.v8` binary
```bash
g++ -I. -Iinclude sheetjs.v8.cc -o sheetjs.v8 -fno-rtti -lv8_monolith \
-lv8_libbase -lv8_libplatform -ldl -Lobj/ -pthread -std=c++17 \
-DV8_COMPRESS_POINTERS=1 -DV8_ENABLE_SANDBOX
```
15) Run the demo:
```bash
./sheetjs.v8 pres.numbers
```
If the program succeeded, the CSV contents will be printed to console and the
file `sheetjsw.xlsb` will be created. That file can be opened with Excel.

@ -0,0 +1,106 @@
/* sheetjs.v8 (C) SheetJS -- https://sheetjs.com */
/* based on the official V8 samples ("BSD-3-Clause") */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include "include/libplatform/libplatform.h"
#include "include/v8.h"
static char *read_file(const char *filename, size_t *sz) {
FILE *f = fopen(filename, "rb");
if(!f) return NULL;
long fsize; { fseek(f, 0, SEEK_END); fsize = ftell(f); fseek(f, 0, SEEK_SET); }
char *buf = (char *)malloc(fsize * sizeof(char));
*sz = fread((void *) buf, 1, fsize, f);
fclose(f);
return buf;
}
v8::Local<v8::Value> eval_code(v8::Isolate *isolate, v8::Local<v8::Context> context, char* code) {
v8::Local<v8::String> source = v8::String::NewFromUtf8(isolate, code).ToLocalChecked();
v8::Local<v8::Script> script = v8::Script::Compile(context, source).ToLocalChecked();
return script->Run(context).ToLocalChecked();
}
#define EVAL_CODE(x) eval_code(isolate, context, (char *)x)
int main(int argc, char* argv[]) {
/* initialize -- this part is from the hello world example */
v8::V8::InitializeICUDefaultLocation(argv[0]);
v8::V8::InitializeExternalStartupData(argv[0]);
std::unique_ptr<v8::Platform> platform = v8::platform::NewDefaultPlatform();
v8::V8::InitializePlatform(platform.get());
v8::V8::Initialize();
v8::Isolate::CreateParams create_params;
create_params.array_buffer_allocator = v8::ArrayBuffer::Allocator::NewDefaultAllocator();
v8::Isolate* isolate = v8::Isolate::New(create_params);
{
v8::Isolate::Scope isolate_scope(isolate);
v8::HandleScope handle_scope(isolate);
v8::Local<v8::Context> context = v8::Context::New(isolate);
v8::Context::Scope context_scope(context);
/* load library */
{
/* read file */
size_t sz; char *file = read_file("xlsx.full.min.js", &sz);
if(!file) { perror("Error reading xlsx.full.min.js"); return 1; }
/* evaluate */
v8::Local<v8::Value> result = EVAL_CODE(file);
/* free */
free(file);
}
/* get version string */
{
v8::Local<v8::Value> result = EVAL_CODE("XLSX.version");
v8::String::Utf8Value vers(isolate, result);
printf("SheetJS library version %s\n", *vers);
}
/* read file */
{
/* read bytes */
size_t sz; char *file = read_file(argv[1], &sz);
if(!file) { perror("Error reading file"); return 1; }
/* copy into array buffer and assign to `buf` in the global scope */
{
std::unique_ptr<v8::BackingStore> back = v8::ArrayBuffer::NewBackingStore(isolate, sz);
memcpy(back->Data(), file, sz);
v8::Local<v8::ArrayBuffer> ab = v8::ArrayBuffer::New(isolate, std::move(back));
v8::Maybe<bool> res = context->Global()->Set(context, v8::String::NewFromUtf8Literal(isolate, "buf"), ab);
}
printf("Loaded file %s\n", argv[1]);
}
/* parse workbook and assign to global `wb` property */
{
v8::Local<v8::Value> result = EVAL_CODE("globalThis.wb = XLSX.read(buf)");
}
/* print CSV of first worksheet */
{
v8::Local<v8::Value> result = EVAL_CODE("XLSX.utils.sheet_to_csv(wb.Sheets[wb.SheetNames[0]])");
v8::String::Utf8Value csv(isolate, result);
printf("%s\n", *csv);
}
// write sheetjsw.xlsb
{
v8::Local<v8::Value> result = EVAL_CODE("XLSX.write(wb, {type:'array', bookType:'xlsb'})");
v8::Local<v8::ArrayBuffer> ab = v8::Local<v8::ArrayBuffer>::Cast(result);
FILE *f = fopen("sheetjsw.xlsb", "wb"); fwrite((char *)ab->Data(), 1, ab->ByteLength(), f); fclose(f);
}
}
/* cleanup -- this part is from the hello world example */
isolate->Dispose();
v8::V8::Dispose();
v8::V8::DisposePlatform();
delete create_params.array_buffer_allocator;
return 0;
}