version bump 1.1.0: zip support

Author: SheetJSDev

.gitignore

@@ -10,18 +10,26 @@ test_files_pres
 *.[cC][sS][vV]
 *.[dD][iIbB][fF]
 *.[pP][rR][nN]
+*.[pP][mM][dD]*
+*.[pP][dD][fF]
 *.[sS][lL][kK]
 *.socialcalc
-*.[xX][lL][sSwWcC]
-*.[xX][lL][sS][xXmMbB]
+*.[xX][lL][sSwWcCaAtTmM]
+*.[xX][lL][sSaAtT][xXmMbB]
 *.[oO][dD][sS]
 *.[fF][oO][dD][sS]
 *.[xX][mM][lL]
 *.[uU][oO][sS]
 *.[wW][kKqQbB][S1234567890]
 *.[qQ][pP][wW]
+*.[bB][iI][fF][fF][23458]
+*.[rR][tT][fF]
+*.[eE][tT][hH]
+*.[zZ][iI][pP]
+*.[mM][sS][iI]
 *.123
 *.htm
 *.html
 *.sheetjs
 *.exe
+*.img

CHANGELOG.md

@@ -4,6 +4,10 @@ This log is intended to keep track of backwards-incompatible changes, including
 but not limited to API changes and file location changes.  Minor behavioral
 changes may not be included if they are not expected to break existing code.
 
+## 1.1.0 (2018-09-04)
+
+* Support for ZIP file format
+
 ## 1.0.6 (2018-04-09)
 
 * `lastIndexOf` in FAT builder enables larger file parsing at minor cost

README.md

@@ -1,13 +1,11 @@
-# Compound File Binary Format
+# Container File Blobs
 
-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)
+Pure JS implementation of various container file formats, including ZIP and CFB.
 
 [![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
@@ -79,29 +77,48 @@ 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, opts)` wraps `parse`.  `opts.type` controls the behavior:
+`CFB.read(blob, opts)` wraps `parse`.
+
+`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.
+
+`CFB.write(cfb, opts)` generates a file based on the container.
+
+`CFB.writeFile(cfb, filename, opts)` creates a file with the specified name.
+
+### Parse Options
+
+`CFB.read` takes an options argument.  `opts.type` controls the behavior:
 
 | `type`     | expected input                                                  |
-|------------|-----------------------------------------------------------------|
+|------------|:----------------------------------------------------------------|
 | `"base64"` | string: Base64 encoding of the file                             |
 | `"binary"` | string: binary string (byte `n` is `data.charCodeAt(n)`)        |
 | `"file"`   | string: path of file that will be read (nodejs only)            |
 | (default)  | buffer or array of 8-bit unsigned int (byte `n` is `data[n]`)   |
 
-`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.
 
-`CFB.write(cfb, opts)` generates a file based on the container.  `opts.type`
-controls the behavior:
+### Write Options
+
+`CFB.write` and `CFB.writeFile` take options argument.
+
+`opts.type` controls the behavior:
 
 | `type`     | output                                                          |
-|------------|-----------------------------------------------------------------|
+|------------|:----------------------------------------------------------------|
 | `"base64"` | string: Base64 encoding of the file                             |
 | `"binary"` | string: binary string (byte `n` is `data.charCodeAt(n)`)        |
 | `"file"`   | string: path of file that will be created (nodejs only)         |
 | (default)  | buffer if available, array of 8-bit unsigned int otherwise      |
 
-`CFB.writeFile(cfb, filename, opts)` creates a file with the specified name.
+`opts.fileType` controls the output file type:
+
+| `fileType`         | output        |
+|:-------------------|:--------------|
+| `'cfb'` (default)  | CFB container |
+| `'zip'`            | ZIP file      |
+
+`opts.compression` enables DEFLATE compression for ZIP file type.
 
 
 ## Utility Functions
@@ -114,6 +131,12 @@ accept a `name` argument strictly deal with absolute file names:
   Set the option `{unsafe:true}` to skip existence checks (for bulk additions)
 - `.cfb_del(cfb, name)` deletes the specified file
 - `.cfb_mov(cfb, old_name, new_name)` moves the old file to new path and name
+- `.use_zlib(require("zlib"))` loads a nodejs zlib instance.
+
+By default, the library uses a pure JS inflate/deflate implementation.  NodeJS
+`zlib.InflateRaw` exposes the number of bytes read in versions after `8.11.0`.
+If a supplied `zlib` does not support the required features, a warning will be
+displayed in the console and the pure JS fallback will be used.
 
 
 ## Container Object Description
@@ -146,11 +169,7 @@ granted by the Apache 2.0 License are reserved by the Original Author.
 
 ## References
 
-
-<details>
-	<summary><b>OSP-covered Specifications</b> (click to show)</summary>
-
  - [MS-CFB]: Compound File Binary File Format
-
-</details>
+ - ZIP `APPNOTE.TXT`: https://pkware.cachefly.net/webdocs/APPNOTE/APPNOTE-6.3.4.TXT
+ - RFC1951: https://www.ietf.org/rfc/rfc1951.txt
 

bin/cfb.njs

@@ -19,11 +19,16 @@ program
 	.option('-O, --to-stdout', 'extract raw contents to stdout')
 	.option('-z, --dump', 'dump internal representation but do not extract')
 	.option('-q, --quiet', 'process but do not report')
+	.option('--here', 'skip the CFB root name when extracting')
+	.option('--osx', 'use OSX-style unzip listing')
+	.option('--zlib', 'use native zlib')
+	.option('--local', 'print times in local timezone')
 	.option('--dev', 'development mode')
 	.option('--read', 'read but do not print out contents');
-
 program.parse(process.argv);
 
+if(program.zlib) X.utils.use_zlib(require('zlib'));
+
 var exit = process.exit;
 var die = function(errno/*:number*/, msg/*:string*/) { console.error(n + ": " + msg); exit(errno); };
 var logit = function(cmd/*:string*/, f/*:string*/) { console.error(sprintf("%-6s %s", cmd, f)); };
@@ -53,30 +58,55 @@ if(program.dump) {
 }
 if(program.repair) { X.writeFile(cfb, program.args[0]); exit(0); }
 
+var rlen = cfb.FullPaths[0].length;
+
 function fix_string(x/*:string*/)/*:string*/ { return x.replace(/[\u0000-\u001f]/g, function($$) { return sprintf("\\u%04X", $$.charCodeAt(0)); }); }
-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 format_date = function(date/*:Date*/, osx/*:?any*/)/*:string*/ {
+	var datefmt = osx ? "%02u-%02u-%04u %02u:%02u": "%02u-%02u-%02u %02u:%02u";
+	var MM = program.local ? date.getMonth() + 1 : date.getUTCMonth() + 1;
+	var DD = program.local ? date.getDate() : date.getUTCDate();
+	var YY = (program.local ? date.getFullYear() : date.getUTCFullYear())%(osx ? 10000 : 100);
+	var hh = program.local ? date.getHours() : date.getUTCHours();
+	var mm = program.local ? date.getMinutes() : date.getUTCMinutes();
+	return sprintf(datefmt, MM, DD, YY, hh, mm);
 };
 
 if(program.listFiles) {
-	var basetime = new Date(1980,0,1);
+	var basetime = new Date(Date.UTC(1980,0,1));
 	var cnt = 0, rootsize = 0, filesize = 0;
-	console.log("  Length     Date   Time    Name");
-	console.log(" --------    ----   ----    ----");
+	var fmtstr = "%9lu  %s   %s";
+	if(program.osx) {
+		console.log("Archive:  " + program.args[0]);
+		console.log("  Length      Date    Time    Name");
+		console.log("---------  ---------- -----   ----");
+		fmtstr = "%9lu  %s   %s";
+	} else {
+		console.log("  Length     Date   Time    Name");
+		console.log(" --------    ----   ----    ----");
+	}
 	cfb.FileIndex.forEach(function(file/*:CFBEntry*/, 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), fix_string(cfb.FullPaths[i])));
+				var fixname = fix_string(cfb.FullPaths[i]);
+				if(program.osx && fixname.match(/\\u0001Sh33tJ5/)) return;
+				if(program.here) fixname = fixname.slice(rlen);
+				console.log(sprintf(fmtstr, file.size, format_date(file.mt || basetime, program.osx), fixname));
 				filesize += file.size;
 				++cnt;
 		}
 	});
-	console.log(" --------                   -------");
-	console.log(sprintf("%9lu                   %lu file%s", rootsize || filesize, cnt, (cnt !== 1 ? "s" : "")));
+	var outfmt = "%9lu                   %lu file%s";
+	if(program.osx) {
+		console.log("---------                     -------");
+		outfmt = "%9lu                     %lu file%s";
+	} else {
+		console.log(" --------                   -------");
+	}
+	console.log(sprintf(outfmt, rootsize || filesize, cnt, (cnt !== 1 ? "s" : "")));
 
 	exit(0);
 }
@@ -124,8 +154,13 @@ if(program.args.length > 1) {
 }
 
 if(program.toStdout) exit(0);
-for(var i=0; i!==cfb.FullPaths.length; ++i) {
+for(var i=program.here ? 1 : 0; i!==cfb.FullPaths.length; ++i) {
 	if(!cfb.FileIndex[i].name) continue;
-	if(cfb.FullPaths[i].slice(-1) === "/") mkdirp(cfb.FullPaths[i]);
-	else write(cfb.FullPaths[i], cfb.FileIndex[i]);
+	var fp = cfb.FullPaths[i];
+	if(program.here) fp = fp.slice(rlen);
+	if(fp.slice(-1) === "/") mkdirp(fp);
+	else {
+		if(fp.indexOf("/") > -1) mkdirp(fp.slice(0, fp.lastIndexOf("/")));
+		write(fp, cfb.FileIndex[i]);
+	}
 }

bits/00_header.js

@@ -2,5 +2,5 @@
 /* vim: set ts=2: */
 /*jshint eqnull:true */
 /*exported CFB */
-/*global module, require:false, process:false, Buffer:false, Uint8Array:false */
+/*global module, require:false, process:false, Buffer:false, Uint8Array:false, Uint16Array:false */
 

bits/05_buf.js

@@ -5,9 +5,11 @@ var Buffer_from = /*::(*/function(){}/*:: :any)*/;
 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);
+	Buffer_from = /*::((*/nbfs ? function(buf, enc) { return (enc) ? new Buffer(buf, enc) : new Buffer(buf); } : Buffer.from.bind(Buffer)/*::) :any)*/;
 	// $FlowIgnore
 	if(!Buffer.alloc) Buffer.alloc = function(n) { return new Buffer(n); };
+	// $FlowIgnore
+	if(!Buffer.allocUnsafe) Buffer.allocUnsafe = function(n) { return new Buffer(n); };
 }
 
 function new_raw_buf(len/*:number*/) {
@@ -16,8 +18,14 @@ function new_raw_buf(len/*:number*/) {
 	/* jshint +W056 */
 }
 
-var s2a = function s2a(s/*:string*/) {
-	if(has_buf) return Buffer.from(s, "binary");
+function new_unsafe_buf(len/*:number*/) {
+	/* jshint -W056 */
+	return has_buf ? Buffer.allocUnsafe(len) : new Array(len);
+	/* jshint +W056 */
+}
+
+var s2a = function s2a(s/*:string*/)/*:any*/ {
+	if(has_buf) return Buffer_from(s, "binary");
 	return s.split("").map(function(x/*:string*/)/*:number*/{ return x.charCodeAt(0) & 0xff; });
 };
 

bits/08_blob.js

@@ -22,7 +22,6 @@ if(has_buf/*:: && typeof Buffer !== 'undefined'*/) {
 	};
 	__hexlify = function(b/*:RawBytes|CFBlob*/,s/*:number*/,l/*:number*/)/*:string*/ { return Buffer.isBuffer(b)/*:: && b instanceof Buffer*/ ? b.toString('hex',s,s+l) : ___hexlify(b,s,l); };
 	__toBuffer = function(bufs/*:Array<Array<RawBytes>>*/)/*:RawBytes*/ { return (bufs[0].length > 0 && Buffer.isBuffer(bufs[0][0])) ? Buffer.concat((bufs[0]/*:any*/)) : ___toBuffer(bufs);};
-	// $FlowIgnore
 	s2a = function(s/*:string*/)/*:RawBytes*/ { return Buffer_from(s, "binary"); };
 	bconcat = function(bufs/*:Array<RawBytes>*/)/*:RawBytes*/ { return Buffer.isBuffer(bufs[0]) ? Buffer.concat(/*::(*/bufs/*:: :any)*/) : __bconcat(bufs); };
 }

bits/21_crc32.js

@@ -0,0 +1,101 @@
+/* crc32.js (C) 2014-present SheetJS -- http://sheetjs.com */
+/* vim: set ts=2: */
+/*exported CRC32 */
+var CRC32;
+(function (factory) {
+	/*jshint ignore:start */
+	/*eslint-disable */
+	factory(CRC32 = {});
+	/*eslint-enable */
+	/*jshint ignore:end */
+}(function(CRC32) {
+CRC32.version = '1.2.0';
+/* see perf/crc32table.js */
+/*global Int32Array */
+function signed_crc_table()/*:any*/ {
+	var c = 0, table/*:Array<number>*/ = new Array(256);
+
+	for(var n =0; n != 256; ++n){
+		c = n;
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		c = ((c&1) ? (-306674912 ^ (c >>> 1)) : (c >>> 1));
+		table[n] = c;
+	}
+
+	return typeof Int32Array !== 'undefined' ? new Int32Array(table) : table;
+}
+
+var T = signed_crc_table();
+function crc32_bstr(bstr/*:string*/, seed/*:number*/)/*:number*/ {
+	var C = seed ^ -1, L = bstr.length - 1;
+	for(var i = 0; i < L;) {
+		C = (C>>>8) ^ T[(C^bstr.charCodeAt(i++))&0xFF];
+		C = (C>>>8) ^ T[(C^bstr.charCodeAt(i++))&0xFF];
+	}
+	if(i === L) C = (C>>>8) ^ T[(C ^ bstr.charCodeAt(i))&0xFF];
+	return C ^ -1;
+}
+
+function crc32_buf(buf/*:Uint8Array|Array<number>*/, seed/*:number*/)/*:number*/ {
+	if(buf.length > 10000) return crc32_buf_8(buf, seed);
+	var C = seed ^ -1, L = buf.length - 3;
+	for(var i = 0; i < L;) {
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+	}
+	while(i < L+3) C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+	return C ^ -1;
+}
+
+function crc32_buf_8(buf/*:Uint8Array|Array<number>*/, seed/*:number*/)/*:number*/ {
+	var C = seed ^ -1, L = buf.length - 7;
+	for(var i = 0; i < L;) {
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+		C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+	}
+	while(i < L+7) C = (C>>>8) ^ T[(C^buf[i++])&0xFF];
+	return C ^ -1;
+}
+
+function crc32_str(str/*:string*/, seed/*:number*/)/*:number*/ {
+	var C = seed ^ -1;
+	for(var i = 0, L=str.length, c, d; i < L;) {
+		c = str.charCodeAt(i++);
+		if(c < 0x80) {
+			C = (C>>>8) ^ T[(C ^ c)&0xFF];
+		} else if(c < 0x800) {
+			C = (C>>>8) ^ T[(C ^ (192|((c>>6)&31)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|(c&63)))&0xFF];
+		} else if(c >= 0xD800 && c < 0xE000) {
+			c = (c&1023)+64; d = str.charCodeAt(i++)&1023;
+			C = (C>>>8) ^ T[(C ^ (240|((c>>8)&7)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|((c>>2)&63)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|((d>>6)&15)|((c&3)<<4)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|(d&63)))&0xFF];
+		} else {
+			C = (C>>>8) ^ T[(C ^ (224|((c>>12)&15)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|((c>>6)&63)))&0xFF];
+			C = (C>>>8) ^ T[(C ^ (128|(c&63)))&0xFF];
+		}
+	}
+	return C ^ -1;
+}
+CRC32.table = T;
+CRC32.bstr = crc32_bstr;
+CRC32.buf = crc32_buf;
+CRC32.str = crc32_str;
+}));

bits/31_version.js

@@ -1 +1 @@
-exports.version = '1.0.8';
+exports.version = '1.1.0';