version bump 0.6.0: case insensitive find

.jshintrc

@@ -0,0 +1,4 @@
+{
+	"bitwise": false,
+	"curly": false
+}

README.md

@@ -4,7 +4,7 @@ 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, DOC, and other Microsoft
 Office file types). 
 
-# Installation and Usage
+# Utility Installation and Usage
 
 The package is available on NPM:
 
@@ -18,6 +18,79 @@ files that line up with the tree-based structure of the storage.  Metadata
 such as the red-black tree are discarded (and in the future, new CFB containers
 will exclusively use black nodes)
 
+# Library Installation and Usage
+
+In the browser:
+
+    <script src="cfb.js" type="text/javascript"></script>
+
+In node:
+
+    var CFB = require('cfb');
+
+For example, to get the Workbook content from an XLS file:
+
+    var cfb = CFB.read(filename, {type: 'file'});
+    var has_vba = cfb.Directory['Workbook']
+
+## API
+
+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:
+
+- `file`: `blob` should be a file name
+- `base64`: `blob` should be a base64 string
+- `binary`: `blob` should be a binary string
+
+## Container Object Description
+
+The object returned by `parse` and `read` can be found in the source (`rval`).
+It has the following properties and methods:
+
+- `.find(path)` performs a case-insensitive match for the path (or file name, if
+  there are no slashes) and returns an entry object (described later) or null if
+  not found 
+
+- `.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
+  the root entry (so the entries are unique)
+
+- `.FullPathDir` is an object whose keys are entries in `.FullPaths` and whose
+  values are objects with metadata and content (described below)
+
+- `.FileIndex` is an array of the objects from `.FullPathDir`, in the same order
+  as `.FullPaths`.
+
+- `.raw` contains the raw header and sectors 
+
+- `.Paths` is an array of the names of all of the streams (files) and storages 
+  (directories) in the container.  There is no disambiguation in the case of
+  streams with the same name.
+
+- `.Directory` is an object whose keys are entries in `.Paths` and whose values
+  are objects with metadata and content.  Since collisions are not properly
+  handled here, `.FullPathDir` is the better option for new projects.
+
+## Entry Object Description
+
+The entry objects are available from `FullPathDir`, `FileIndex`, and `Directory`
+elements of the container object.
+
+- `.name` is the (case sensitive) internal name
+- `.type` is the type (`stream` for files, `storage` for dirs, `root` for root)
+- `.content` is a Buffer/Array with the raw content
+- `.ct`/`.mt` are the creation and modification time (if provided in file)
+
+# Notes
+
+Case comparison has not been verified for non-ASCII character
+
+Writing is not supported.  It is in the works, but it has not yet been released.
+
 # License
 
 This implementation is covered under Apache 2.0 license.  It complies with the

cfb.js

@@ -355,6 +355,7 @@ function read_directory(idx) {
 }
 read_directory(dir_start);
 
+/* [MS-CFB] 2.6.4 Red-Black Tree */
 function build_full_paths(Dir, pathobj, paths, patharr) {
 	var i;
 	var dad = new Array(patharr.length);
@@ -389,13 +390,24 @@ build_full_paths(FileIndex, FullPathDir, FullPaths, Paths);
 var root_name = Paths.shift();
 Paths.root = root_name;
 
+/* [MS-CFB] 2.6.4 (Unicode 3.0.1 case conversion) */
+function find_path(path) {
+	if(path[0] === "/") path = root_name + path;
+	var UCNames = (path.indexOf("/") !== -1 ? FullPaths : Paths).map(function(x) { return x.toUpperCase(); });
+	var UCPath = path.toUpperCase();
+	var w = UCNames.indexOf(UCPath);
+	if(w === -1) return null;
+	return path.indexOf("/") !== -1 ? FileIndex[w] : files[Paths[w]];
+}
+
 var rval = {
 	raw: {header: header, sectors: sectors},
 	Paths: Paths,
 	FileIndex: FileIndex,
 	FullPaths: FullPaths,
 	FullPathDir: FullPathDir,
-	Directory: files
+	Directory: files,
+	find: find_path
 };
 
 return rval;

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "cfb",
-	"version": "0.5.0",
+	"version": "0.6.0",
 	"author": "Niggler",
 	"description": "Compound File Binary File Format extractor",
 	"keywords": [ "cfb", "compression", "office" ],

test.js

@@ -1,11 +1,26 @@
+/* vim: set ts=2: */
 var CFB;
 var fs = require('fs');
 describe('source', function() { it('should load', function() { CFB = require('./'); }); });
+
 var files = fs.readdirSync('test_files').filter(function(x){return x.substr(-4)==".xls";});
-files.forEach(function(x) {
-	describe(x, function() {
+
+function parsetest(x, cfb) {
+	describe(x + ' should have basic parts', function() {
+		it('should find relative path', function() {
+			if(!cfb.find('Workbook') && !cfb.find('Book')) throw new Error("Cannot find workbook for " + x);
+		});
+		it('should find absolute path', function() {
+			if(!cfb.find('/Workbook') && !cfb.find('/Book')) throw new Error("Cannot find workbook for " + x);
+		});
+	});
+}
+
+describe('should parse test files', function() {
+	files.forEach(function(x) {
 		it('should parse ' + x, function() {
 			var cfb = CFB.read('./test_files/' + x, {type: "file"});
+			parsetest(x, cfb);
 		});
 	});
 });