version bump 0.13.0: write

.flowconfig

@@ -1,6 +1,8 @@
 [ignore]
 .*/node_modules/.*
 .*/dist/.*
+.*/test_files/.*
+.*/test_files_pres/.*
 .*/test.js
 
 .*/bits/.*
@@ -11,7 +13,6 @@
 .*/demo/browser.js
 .*/shim.js
 
-.*/odsbits/.*
 .*/xlscfb.js
 .*/cfb.js
 .*/jszip.js

.gitignore

@@ -1,8 +1,27 @@
 node_modules
+package-lock.json
+*.tgz
 misc/coverage.html
 prof.js
 v8.log
 test_files
 test_files_pres
-*.xls
+*.[tT][xX][tT]
+*.[cC][sS][vV]
+*.[dD][iIbB][fF]
+*.[pP][rR][nN]
+*.[sS][lL][kK]
+*.socialcalc
+*.[xX][lL][sSwWcC]
+*.[xX][lL][sS][xXmMbB]
+*.[oO][dD][sS]
+*.[fF][oO][dD][sS]
+*.[xX][mM][lL]
+*.[uU][oO][sS]
+*.[wW][kKqQbB][S1234567890]
+*.[qQ][pP][wW]
+*.123
+*.htm
+*.html
 *.sheetjs
+*.exe

.travis.yml

@@ -13,7 +13,7 @@ before_install:
   - "npm install -g npm@4.3.0"
   - "npm install -g mocha@2.x voc"
   - "npm install blanket"
-  - "npm install xlsjs"
+  - "npm install xlsjs crc-32"
   - "npm install coveralls mocha-lcov-reporter"
 before_script:
   - "make init"

Makefile

@@ -12,7 +12,7 @@ DEPS=$(sort $(wildcard bits/*.js))
 TARGET=$(LIB).js
 FLOWTARGET=$(LIB).flow.js
 FLOWTGTS=$(TARGET) $(AUXTARGETS)
-UGLIFYOPTS=--support-ie8
+UGLIFYOPTS=--support-ie8 -m
 CLOSURE=/usr/local/lib/node_modules/google-closure-compiler/compiler.jar
 
 ## Main Targets
@@ -48,7 +48,7 @@ init: ## Initial setup for development
 dist: dist-deps $(TARGET) ## Prepare JS files for distribution
 	cp $(TARGET) dist/
 	cp LICENSE dist/
-	uglifyjs $(UGLIFYOPTS) $(TARGET) -o dist/$(LIB).min.js --source-map dist/$(LIB).min.map --preamble "$$(head -n 1 bits/00_header.js)"
+	uglifyjs $(TARGET) $(UGLIFYOPTS) -o dist/$(LIB).min.js --source-map dist/$(LIB).min.map --preamble "$$(head -n 1 bits/00_header.js)"
 	misc/strip_sourcemap.sh dist/$(LIB).min.js
 
 .PHONY: dist-deps
@@ -102,7 +102,7 @@ tslint: $(TARGET) ## Run typescript checks
 
 .PHONY: flow
 flow: lint ## Run flow checker
-	@flow check --all --show-all-errors
+	@flow check --all --show-all-errors --include-warnings
 
 .PHONY: cov
 cov: misc/coverage.html ## Run coverage test

README.md

@@ -1,28 +1,33 @@
 # Compound File Binary Format
 
-This is a Pure-JS implementation of MS-CFB: Compound File Binary File Format, a
-format used in many Microsoft file types (such as XLS and DOC)
+Pure-JS implementation of MS-CFB: Compound File Binary File Format, a container
+format used in many Microsoft file types (XLS, DOC, VBA blobs in XLSX and XLSB)
 
-# Utility Installation and Usage
+[![Build Status](https://travis-ci.org/SheetJS/js-cfb.svg?branch=master)](https://travis-ci.org/SheetJS/js-cfb)
+[![Coverage Status](http://img.shields.io/coveralls/SheetJS/js-cfb/master.svg)](https://coveralls.io/r/SheetJS/js-cfb?branch=master)
+[![Dependencies Status](https://david-dm.org/sheetjs/js-cfb/status.svg)](https://david-dm.org/sheetjs/js-cfb)
+[![NPM Downloads](https://img.shields.io/npm/dt/cfb.svg)](https://npmjs.org/package/cfb)
+[![ghit.me](https://ghit.me/badge.svg?repo=sheetjs/js-xlsx)](https://ghit.me/repo/sheetjs/js-xlsx)
+[![Analytics](https://ga-beacon.appspot.com/UA-36810333-1/SheetJS/js-cfb?pixel)](https://github.com/SheetJS/js-cfb)
+
+## Installation
+
+In the browser:
+
+```html
+<script src="dist/cfb.min.js" type="text/javascript"></script>
+```
 
 With [npm](https://www.npmjs.org/package/cfb):
 
 ```bash
-$ npm install -g cfb
-$ cfb path/to/CFB/file
+$ npm install cfb
 ```
 
-The command will extract the storages and streams in the container, generating
-files that line up with the tree-based structure of the storage.  Metadata such
-as the red-black tree are discarded.  The `-l` option displays a manifest.
-
-# Library Installation and Usage
+The `xlscfb.js` file is designed to be embedded in [js-xlsx](http://git.io/xlsx)
 
-In the browser:
 
-```html
-<script src="cfb.js" type="text/javascript"></script>
-```
+## Library Usage
 
 In node:
 
@@ -34,36 +39,72 @@ For example, to get the Workbook content from an XLS file:
 
 ```js
 var cfb = CFB.read(filename, {type: 'file'});
-var workbook = cfb.find('Workbook');
+var workbook = CFB.find(cfb, 'Workbook');
 var data = workbook.content;
 ```
 
-The `xlscfb.js` file is designed to be embedded in [js-xlsx](http://git.io/xlsx)
 
-# API
+## Command-Line Utility Usage
+
+It is preferable to install the library globally with npm:
 
-Typescript definitions are maintained in `types/index.d.ts`.
+```bash
+$ npm install -g cfb
+```
+
+The global installation adds a command `cfb` which can work with existing files:
+
+- `cfb file` will extract the contents of the file to the current directory.
+  It will make the corresponding subdirectories.
+- `cfb --list-files file` will show a listing of the contained files.
+  The format follows the `unzip -l` "short format".
+- `cfb --repair file` will attempt to repair by reading and re-writing the file.
+  This fixes some issues with files generated by non-standard tools.
+
+
+## JS API
+
+TypeScript definitions are maintained in `types/index.d.ts`.
 
 The CFB object exposes the following methods and properties:
 
 `CFB.parse(blob)` takes a nodejs Buffer or an array of bytes and returns an
 parsed representation of the data.
 
-`CFB.read(blob, options)` wraps `parse`.  `options.type` controls the behavior:
+`CFB.read(blob, opts)` wraps `parse`.  `opts.type` controls the behavior:
 
-- `file`: `blob` should be a file name
-- `base64`: `blob` should be a base64 string
-- `binary`: `blob` should be a binary string
+- `file`:   `blob` is interpreted as a file name that will be read
+- `base64`: `blob` is interpreted as base64 string
+- `binary`: `blob` is interpreted as binary string
+- default:  `blob` is interpreted as nodejs buffer or array of bytes
 
 `CFB.find(cfb, path)` performs a case-insensitive match for the path (or file
 name, if there are no slashes) and returns an entry object or null if not found.
 
-## Container Object Description
+`CFB.write(cfb, opts)` generates a file based on the container.  `opts.type`
+controls the behavior:
+
+- `base64`: returns a base64 string
+- `binary`: returns a binary string
+- default:  returns a nodejs buffer or array of bytes
+
+`CFB.writeFile(cfb, filename, opts)` creates a file with the specified name.
+
+
+## Utility Functions
+
+The utility functions are available in the `CFB.utils` object.  Functions that
+accept a `name` argument strictly deal with absolute file names:
 
-The object returned by `parse` and `read` can be found in the source (`rval`).
-It has the following properties and methods:
+- `.cfb_new(?opts)` creates a new container object.
+- `.cfb_add(cfb, name, ?content, ?opts)` adds a new file to the `cfb`.
+- `.cfb_del(cfb, name)` deletes the specified file
+- `.cfb_mov(cfb, old_name, new_name)` moves the old file to new path and name
 
-- `.find(path)` is equivalent to `CFB.find(cfb, path)` and should not be used.
+
+## Container Object Description
+
+The objects returned by `parse` and `read` have the following properties:
 
 - `.FullPaths` is an array of the names of all of the streams (files) and
   storages (directories) in the container.  The paths are properly prefixed from
@@ -77,32 +118,37 @@ It has the following properties and methods:
 
 - `.raw` contains the raw header and sectors
 
+
 ## Entry Object Description
 
 The entry objects are available from `FullPathDir` and `FileIndex` elements of
-the container object.
+the container object:
+
+```typescript
+interface CFBEntry {
+  name: string; /** Case-sensitive internal name */
+  type: number; /** 1 = dir, 2 = file, 5 = root ; see [MS-CFB] 2.6.1 */
+  content: Buffer | number[] | Uint8Array; /** Raw Content */
+  ct?: Date; /** Creation Time */
+  mt?: Date; /** Modification Time */
+}
+```
 
-- `.name` is the (case sensitive) internal name
-- `.type` is the type as defined in "Object Type" in [MS-CFB] 2.6.1:
-  `2 (stream)` for files, `1 (storage)` for dirs, `5 (root)` for root)
-- `.content` is a Buffer/Array with the raw content
-- `.ct`/`.mt` are the creation and modification time (if provided in file)
 
-# License
+## License
 
-This implementation is covered under Apache 2.0 license.  It complies with the
-[Open Specifications Promise](http://www.microsoft.com/openspecifications/)
+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.
 
-[![Build Status](https://travis-ci.org/SheetJS/js-cfb.svg?branch=master)](https://travis-ci.org/SheetJS/js-cfb)
 
-[![Coverage Status](http://img.shields.io/coveralls/SheetJS/js-cfb/master.svg)](https://coveralls.io/r/SheetJS/js-cfb?branch=master)
+## References
 
-[![Analytics](https://ga-beacon.appspot.com/UA-36810333-1/SheetJS/js-cfb?pixel)](https://github.com/SheetJS/js-cfb)
 
-[![NPM Downloads](https://img.shields.io/npm/dt/cfb.svg)](https://npmjs.org/package/cfb)
+<details>
+	<summary><b>OSP-covered Specifications</b> (click to show)</summary>
 
-[![Dependencies Status](https://david-dm.org/sheetjs/js-cfb/status.svg)](https://david-dm.org/sheetjs/js-cfb)
+ - [MS-CFB]: Compound File Binary File Format
 
-[![ghit.me](https://ghit.me/badge.svg?repo=sheetjs/js-cfb)](https://ghit.me/repo/sheetjs/js-cfb)
+</details>
 
 

bin/cfb.njs

@@ -3,13 +3,16 @@
 /* eslint-env node */
 /* vim: set ts=2 ft=javascript: */
 var X = require('../');
-var fs = require('fs'), program = require('commander');
+var fs = require('fs');
+var program = require('commander');
+var PRINTJ = require("printj");
 program
 	.version(X.version)
 	.usage('[options] <file>')
 	.option('-q, --quiet', 'process but do not report')
 	.option('-l, --list-files', 'list files')
 	.option('-d, --dump', 'dump internal representation but do not extract')
+	.option('-r, --repair', 'attempt to repair and garbage-collect archive')
 	.option('--dev', 'development mode')
 	.option('--read', 'read but do not print out contents');
 
@@ -33,26 +36,30 @@ if(program.dump) {
 	console.log(cfb.FullPathDir);
 	process.exit(0);
 }
-if(program.listFiles) {
-	var PRINTJ = require("printj"), sprintf = PRINTJ.sprintf;
+if(program.repair) {
+	X.writeFile(cfb, program.args[0]);
+	process.exit(0);
+}
 
+var sprintf = PRINTJ.sprintf;
+function fix_string(x/*:string*/)/*:string*/ { return x.replace(/[\u0000-\u001f]/, function($$) { return sprintf("\\u%04X", $$.charCodeAt(0)); }); }
+if(program.listFiles) {
 	var format_date = function(date/*:Date*/)/*:string*/ {
 		return sprintf("%02u-%02u-%02u %02u:%02u", date.getUTCMonth()+1, date.getUTCDate(), date.getUTCFullYear()%100, date.getUTCHours(), date.getUTCMinutes());
 	};
 
 	var basetime = new Date(1980,0,1);
-	var cnt = 0;
-	var rootsize = 0, filesize = 0;
+	var cnt = 0, rootsize = 0, filesize = 0;
 	console.log("  Length     Date   Time    Name");
 	console.log(" --------    ----   ----    ----");
-	cfb.FileIndex.forEach(function(file, i) {
+	cfb.FileIndex.forEach(function(file, i/*:number*/) {
 		switch(file.type) {
 			case 5:
 				basetime = file.ct || file.mt || basetime;
 				rootsize = file.size;
 				break;
 			case 2:
-				console.log(sprintf("%9lu  %s   %s", file.size, format_date(basetime), cfb.FullPaths[i]));
+				console.log(sprintf("%9lu  %s   %s", file.size, format_date(basetime), fix_string(cfb.FullPaths[i])));
 				filesize += file.size;
 				++cnt;
 		}
@@ -64,10 +71,10 @@ if(program.listFiles) {
 }
 for(var i=0; i!==cfb.FullPaths.length; ++i) {
 	if(cfb.FullPaths[i].slice(-1) === "/") {
-		console.error("mkdir " + cfb.FullPaths[i]);
+		console.error("mkdir " + fix_string(cfb.FullPaths[i]));
 		fs.mkdirSync(cfb.FullPaths[i]);
 	} else {
-		console.error("writing " + cfb.FullPaths[i]);
+		console.error("write " + fix_string(cfb.FullPaths[i]));
 		fs.writeFileSync(cfb.FullPaths[i], /*::new Buffer((*/cfb.FileIndex[i].content/*:: :any))*/);
 	}
 }

bits/00_header.js

@@ -1,4 +1,6 @@
 /* cfb.js (C) 2013-present SheetJS -- http://sheetjs.com */
 /* vim: set ts=2: */
 /*jshint eqnull:true */
+/*exported CFB */
+/*global module, require:false, process:false, Buffer:false, Uint8Array:false */
 

bits/04_base64.js

@@ -0,0 +1,46 @@
+var Base64 = (function make_b64(){
+	var map = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/=";
+	return {
+		encode: function(input/*:string*/)/*:string*/ {
+			var o = "";
+			var c1/*:number*/, c2/*:number*/, c3/*:number*/;
+			var e1/*:number*/, e2/*:number*/, e3/*:number*/, e4/*:number*/;
+			for(var i = 0; i < input.length; ) {
+				c1 = input.charCodeAt(i++);
+				e1 = (c1 >> 2);
+
+				c2 = input.charCodeAt(i++);
+				e2 = ((c1 & 3) << 4) | (c2 >> 4);
+
+				c3 = input.charCodeAt(i++);
+				e3 = ((c2 & 15) << 2) | (c3 >> 6);
+				e4 = (c3 & 63);
+				if (isNaN(c2)) { e3 = e4 = 64; }
+				else if (isNaN(c3)) { e4 = 64; }
+				o += map.charAt(e1) + map.charAt(e2) + map.charAt(e3) + map.charAt(e4);
+			}
+			return o;
+		},
+		decode: function b64_decode(input/*:string*/)/*:string*/ {
+			var o = "";
+			var c1/*:number*/, c2/*:number*/, c3/*:number*/;
+			var e1/*:number*/, e2/*:number*/, e3/*:number*/, e4/*:number*/;
+			input = input.replace(/[^\w\+\/\=]/g, "");
+			for(var i = 0; i < input.length;) {
+				e1 = map.indexOf(input.charAt(i++));
+				e2 = map.indexOf(input.charAt(i++));
+				c1 = (e1 << 2) | (e2 >> 4);
+				o += String.fromCharCode(c1);
+
+				e3 = map.indexOf(input.charAt(i++));
+				c2 = ((e2 & 15) << 4) | (e3 >> 2);
+				if (e3 !== 64) { o += String.fromCharCode(c2); }
+
+				e4 = map.indexOf(input.charAt(i++));
+				c3 = ((e3 & 3) << 6) | e4;
+				if (e4 !== 64) { o += String.fromCharCode(c3); }
+			}
+			return o;
+		}
+	};
+})();