Release v1.0.1

fix issue #16

.jscs.json

@@ -0,0 +1,34 @@
+{
+    "requireCurlyBraces": ["if", "else", "for", "while", "do", "try", "catch"],
+    "requireSpaceAfterKeywords": ["if", "else", "for", "while", "do", "switch", "return", "try", "catch"],
+    "requireParenthesesAroundIIFE": true,
+    "requireSpacesInFunctionExpression": {
+        "beforeOpeningCurlyBrace": true
+    },
+    "requireSpacesInAnonymousFunctionExpression": {
+        "beforeOpeningRoundBrace": true
+    },
+    "disallowSpacesInNamedFunctionExpression": {
+        "beforeOpeningRoundBrace": true
+    },
+    "disallowSpacesInFunctionDeclaration": {
+        "beforeOpeningRoundBrace": true
+    },
+    "disallowMultipleVarDecl": true,
+    "requireSpacesInsideObjectBrackets": "all",
+    "disallowSpaceAfterObjectKeys": true,
+    "requireCommaBeforeLineBreak": true,
+    "disallowSpaceBeforeBinaryOperators": [","],
+    "disallowSpaceAfterPrefixUnaryOperators": ["++", "--", "+", "-", "~", "!"],
+    "disallowSpaceBeforePostfixUnaryOperators": ["++", "--"],
+    "requireSpaceBeforeBinaryOperators": ["+", "-", "/", "*", "=", "==", "===", "!=", "!==", ">", ">=", "<", "<="],
+    "requireSpaceAfterBinaryOperators": [",", "+", "-", "/", "*", "=", "==", "===", "!=", "!==", ">", ">=", "<", "<="],
+    "validateQuoteMarks": true,
+    "validateIndentation": 4,
+    "disallowTrailingWhitespace": true,
+    "disallowKeywordsOnNewLine": ["else"],
+    "requireCapitalizedConstructors": true,
+    "safeContextKeyword": "self",
+    "requireDotNotation": true,
+    "disallowYodaConditions": true
+}

.travis.yml

@@ -1,7 +1,6 @@
 language: node_js
 node_js:
-  - "0.8"
   - "0.10"
   - "0.11"
-before_script:
+before_install:
   - npm install -g grunt-cli

Gruntfile.coffee

@@ -5,6 +5,7 @@ module.exports = (grunt) ->
     @loadNpmTasks('grunt-contrib-jshint')
     @loadNpmTasks('grunt-contrib-uglify')
     @loadNpmTasks('grunt-contrib-watch')
+    @loadNpmTasks('grunt-jscs-checker')
     @loadNpmTasks('grunt-mocha-cli')
 
     @initConfig
@@ -16,6 +17,13 @@ module.exports = (grunt) ->
             options:
                 jshintrc: '.jshintrc'
 
+        jscs:
+            src:
+                options:
+                    config: '.jscs.json'
+                files:
+                    src: [ 'lib/*.js', 'test/*.js' ]
+
         watch:
             all:
                 options:
@@ -49,5 +57,5 @@ module.exports = (grunt) ->
                 pushTo: 'origin'
 
     @registerTask 'default', ['test']
-    @registerTask 'build', ['clean', 'jshint', 'browserify', 'uglify']
+    @registerTask 'build', ['clean', 'jshint', 'jscs', 'browserify', 'uglify']
     @registerTask 'test', ['build', 'mochacli']

README.md

@@ -88,11 +88,12 @@ The `PO` class exposes the following members:
 * `msgstr`: An array of translated strings. Items that have no plural msgid
   only have one element in this array.
 * `references`: An array of reference strings.
-* `comments`: An array of string comments.
+* `comments`: An array of string translator comments.
+* `extractedComments`: An array of string extracted comments.
 * `flags`: A dictionary of the string flags. Each flag is mapped to a key with
   value true. For instance, a string with the fuzzy flag set will have
   `item.flags.fuzzy == true`.
-* `msgctxt`: context of the message, an arbitrary string, can be used for disambiguation
+* `msgctxt`: Context of the message, an arbitrary string, can be used for disambiguation.
 
 
 ## Contributing

bower.json

@@ -1,6 +1,6 @@
 {
   "name": "pofile",
-  "version": "0.2.4",
+  "version": "1.0.1",
   "authors": [
     "Ruben Vermeersch <ruben@rocketeer.be>"
   ],

dist/pofile.js

@@ -1,6 +1,6 @@
 require=(function e(t,n,r){function s(o,u){if(!n[o]){if(!t[o]){var a=typeof require=="function"&&require;if(!u&&a)return a(o,!0);if(i)return i(o,!0);throw new Error("Cannot find module '"+o+"'")}var f=n[o]={exports:{}};t[o][0].call(f.exports,function(e){var n=t[o][1][e];return s(n?n:e)},f,f.exports,e,t,n,r)}return n[o].exports}var i=typeof require=="function"&&require;for(var o=0;o<r.length;o++)s(r[o]);return s})({"W8CkM0":[function(require,module,exports){
-var fs = require('fs'),
-    isArray = require('lodash.isarray');
+var fs = require('fs');
+var isArray = require('lodash.isarray');
 
 function trim(string) {
     return string.replace(/^\s+|\s+$/g, '');
@@ -8,6 +8,7 @@ function trim(string) {
 
 var PO = function () {
     this.comments = [];
+    this.extractedComments = [];
     this.headers = {};
     this.items = [];
 };
@@ -17,21 +18,26 @@ PO.prototype.save = function (filename, callback) {
 };
 
 PO.prototype.toString = function () {
-    var lines = [],
-        that = this;
+    var lines = [];
 
     if (this.comments) {
         this.comments.forEach(function (comment) {
             lines.push('# ' + comment);
         });
     }
+    if (this.extractedComments) {
+        this.extractedComments.forEach(function (comment) {
+            lines.push('#. ' + comment);
+        });
+    }
 
     lines.push('msgid ""');
     lines.push('msgstr ""');
 
     var keys = Object.keys(this.headers);
+    var self = this;
     keys.forEach(function (key) {
-        lines.push('"' + key + ': ' + that.headers[key] + '\\n"');
+        lines.push('"' + key + ': ' + self.headers[key] + '\\n"');
     });
 
     lines.push('');
@@ -41,7 +47,7 @@ PO.prototype.toString = function () {
         lines.push('');
     });
 
-    return lines.join("\n");
+    return lines.join('\n');
 };
 
 PO.load = function (filename, callback) {
@@ -57,10 +63,15 @@ PO.load = function (filename, callback) {
 PO.parse = function (data) {
     //support both unix and windows newline formats.
     data = data.replace(/\r\n/g, '\n');
-    var po = new PO(),
-        sections = data.split(/\n\n/),
-        headers = sections.shift(),
-        lines = sections.join("\n").split(/\n/);
+    var po = new PO();
+    var sections = data.split(/\n\n/);
+    var headers = [sections.shift()];
+    //everything until the first 'msgid ""' is considered header
+    while (headers[headers.length - 1].indexOf('msgid ""') < 0) {
+        headers.push(sections.shift());
+    }
+    headers = headers.join('\n');
+    var lines = sections.join('\n').split(/\n/);
 
     po.headers = {
         'Project-Id-Version': '',
@@ -75,25 +86,44 @@ PO.parse = function (data) {
         'Plural-Forms': '',
     };
 
-    headers.split(/\n/).forEach(function (header) {
-        if (header.match(/^#/)) {
-            po.comments.push(header.replace(/^#\s*/, ''));
+    headers.split(/\n/).reduce(function (acc, line) {
+        if (acc.merge) {
+            //join lines, remove last resp. first "
+            line = acc.pop().slice(0, -1) + line.slice(1);
+            delete acc.merge;
         }
-        if (header.match(/^"/)) {
+        if (/^".*"$/.test(line) && !/^".*\\n"$/.test(line)) {
+            acc.merge = true;
+        }
+        acc.push(line);
+        return acc;
+    }, []).forEach(function (header) {
+        if (header.match(/^#\./)) {
+            po.extractedComments.push(header.replace(/^#\.\s*/, ''));
+        } else if (header.match(/^#/)) {
+            po.comments.push(header.replace(/^#\s*/, ''));
+        } else if (header.match(/^"/)) {
             header = header.trim().replace(/^"/, '').replace(/\\n"$/, '');
-            var p = header.split(/:/),
-                name = p.shift().trim(),
-                value = p.join(':').trim();
+            var p = header.split(/:/);
+            var name = p.shift().trim();
+            var value = p.join(':').trim();
             po.headers[name] = value;
         }
     });
 
-    var item = new PO.Item(),
-        context = null,
-        plural = 0;
+    var item = new PO.Item();
+    var context = null;
+    var plural = 0;
+    var obsoleteCount = 0;
+    var noCommentLineCount = 0;
 
     function finish() {
         if (item.msgid.length > 0) {
+            if (obsoleteCount >= noCommentLineCount) {
+                item.obsolete = true;
+            }
+            obsoleteCount = 0;
+            noCommentLineCount = 0;
             po.items.push(item);
             item = new PO.Item();
         }
@@ -102,61 +132,99 @@ PO.parse = function (data) {
     function extract(string) {
         string = trim(string);
         string = string.replace(/^[^"]*"|"$/g, '');
-        string = string.replace(/\\"/g, '"');
-        string = string.replace(/\\\\/g, '\\');
+        string = string.replace(/\\([abtnvfr'"\\?]|([0-7]{3})|x([0-9a-fA-F]{2}))/g, function (match, esc, oct, hex) {
+            if (oct) {
+                return String.fromCharCode(parseInt(oct, 8));
+            }
+            if (hex) {
+                return String.fromCharCode(parseInt(hex, 16));
+            }
+            switch (esc) {
+                case 'a':
+                    return '\x07';
+                case 'b':
+                    return '\b';
+                case 't':
+                    return '\t';
+                case 'n':
+                    return '\n';
+                case 'v':
+                    return '\v';
+                case 'f':
+                    return '\f';
+                case 'r':
+                    return '\r';
+                default:
+                    return esc;
+            }
+        });
         return string;
     }
 
     while (lines.length > 0) {
-        var line = trim(lines.shift()),
-            add = false;
+        var line = trim(lines.shift());
+        var lineObsolete = false;
+        var add = false;
+
+        if (line.match(/^#\~/)) { // Obsolete item
+            //only remove the obsolte comment mark, here
+            //might be, this is a new item, so
+            //only remember, this line is marked obsolete, count after line is parsed
+            line = trim(line.substring(2));
+            lineObsolete = true;
+        }
+
         if (line.match(/^#:/)) { // Reference
             finish();
             item.references.push(trim(line.replace(/^#:/, '')));
-        }
-        else if (line.match(/^#,/)) { // Flags
+        } else if (line.match(/^#,/)) { // Flags
             finish();
-            var flags = trim(line.replace(/^#,/, '')).split(",");
+            var flags = trim(line.replace(/^#,/, '')).split(',');
             for (var i = 0; i < flags.length; i++) {
                 item.flags[flags[i]] = true;
             }
-        }
-        else if (line.match(/^#/)) { // Comment
+        } else if (line.match(/^#($|\s+)/)) { // Translator comment
             finish();
-            item.comments.push(trim(line.replace(/^#/, '')));
-        }
-        else if (line.match(/^msgid_plural/)) { // Plural form
+            item.comments.push(trim(line.replace(/^#($|\s+)/, '')));
+        } else if (line.match(/^#\./)) { // Extracted comment
+            finish();
+            item.extractedComments.push(trim(line.replace(/^#\./, '')));
+        } else if (line.match(/^msgid_plural/)) { // Plural form
             item.msgid_plural = extract(line);
             context = 'msgid_plural';
-        }
-        else if (line.match(/^msgid/)) { // Original
+            noCommentLineCount++;
+        } else if (line.match(/^msgid/)) { // Original
             finish();
             item.msgid = extract(line);
             context = 'msgid';
-        }
-        else if (line.match(/^msgstr/)) { // Translation
+            noCommentLineCount++;
+        } else if (line.match(/^msgstr/)) { // Translation
             var m = line.match(/^msgstr\[(\d+)\]/);
             plural = m && m[1] ? parseInt(m[1]) : 0;
             item.msgstr[plural] = extract(line);
             context = 'msgstr';
-        }
-        else if (line.match(/^msgctxt/)) { // Context
+            noCommentLineCount++;
+        } else if (line.match(/^msgctxt/)) { // Context
             finish();
             item.msgctxt = extract(line);
-        }
-        else { // Probably multiline string or blank
+            noCommentLineCount++;
+        } else { // Probably multiline string or blank
             if (line.length > 0) {
+                noCommentLineCount++;
                 if (context === 'msgstr') {
                     item.msgstr[plural] += extract(line);
-                }
-                else if (context === 'msgid') {
+                } else if (context === 'msgid') {
                     item.msgid += extract(line);
-                }
-                else if (context === 'msgid_plural') {
+                } else if (context === 'msgid_plural') {
                     item.msgid_plural += extract(line);
                 }
             }
         }
+
+        if (lineObsolete) {
+            // Count obsolete lines for this item
+            obsoleteCount++;
+        }
     }
     finish();
 
@@ -169,57 +237,99 @@ PO.Item = function () {
     this.references = [];
     this.msgid_plural = null;
     this.msgstr = [];
-    this.comments = [];
+    this.comments = []; // translator comments
+    this.extractedComments = [];
     this.flags = {};
+    this.obsolete = false;
 };
 
 PO.Item.prototype.toString = function () {
-    var lines = [],
-        that = this;
+    var lines = [];
+    var self = this;
+
+    // reverse what extract(string) method during PO.parse does
+    var _escape = function (string) {
+        // don't unescape \n, since string can never contain it
+        // since split('\n') is called on it
+        string = string.replace(/[\x07\b\t\v\f\r"\\]/g, function (match) {
+            switch (match) {
+                case '\x07':
+                    return '\\a';
+                case '\b':
+                    return '\\b';
+                case '\t':
+                    return '\\t';
+                case '\v':
+                    return '\\v';
+                case '\f':
+                    return '\\f';
+                case '\r':
+                    return '\\r';
+                default:
+                    return '\\' + match;
+            }
+        });
+        return string;
+    };
 
     var _process = function (keyword, text, i) {
-        var lines = [],
-            parts = text.split(/\n/),
-            index = typeof i !== 'undefined' ? '[' + i + ']' : '';
+        var lines = [];
+        var parts = text.split(/\n/);
+        var index = typeof i !== 'undefined' ? '[' + i + ']' : '';
         if (parts.length > 1) {
             lines.push(keyword + index + ' ""');
             parts.forEach(function (part) {
-                lines.push('"' + part + '"');
+                lines.push('"' + _escape(part) + '"');
             });
-        }
-        else {
-            lines.push(keyword + index + ' "' + text + '"');
+        } else {
+            lines.push(keyword + index + ' "' + _escape(text) + '"');
         }
         return lines;
     };
 
-    if (this.references.length > 0) {
-        this.references.forEach(function (ref) {
-            lines.push('#: ' + ref);
-        });
-    }
+    // https://www.gnu.org/software/gettext/manual/html_node/PO-Files.html
+    // says order is translator-comments, extracted-comments, references, flags
 
-    var flags = Object.keys(this.flags);
+    this.comments.forEach(function (c) {
+        lines.push('# ' + c);
+    });
+
+    this.extractedComments.forEach(function (c) {
+        lines.push('#. ' + c);
+    });
+
+    this.references.forEach(function (ref) {
+        lines.push('#: ' + ref);
+    });
+
+    var flags = Object.keys(this.flags).filter(function (flag) {
+        return !!this.flags[flag];
+    }, this);
     if (flags.length > 0) {
-        lines.push('#, ' + flags.join(","));
+        lines.push('#, ' + flags.join(','));
     }
+    var mkObsolete = this.obsolete ? '#~ ' : '';
 
     ['msgctxt', 'msgid', 'msgid_plural', 'msgstr'].forEach(function (keyword) {
-        var text = that[keyword];
+        var text = self[keyword];
         if (text != null) {
             if (isArray(text) && text.length > 1) {
                 text.forEach(function (t, i) {
-                    lines = lines.concat(_process(keyword, t, i));
+                    lines = lines.concat(mkObsolete + _process(keyword, t, i));
                 });
-            }
-            else {
+            } else {
                 text = isArray(text) ? text.join() : text;
-                lines = lines.concat(_process(keyword, text));
+                var processed = _process(keyword, text);
+                //handle \n in single-line texts (can not be handled in _escape)
+                for (var i = 1; i < processed.length - 1; i++) {
+                    processed[i] = processed[i].slice(0, -1) + '\\n"';
+                }
+                lines = lines.concat(mkObsolete + processed.join('\n' + mkObsolete));
             }
         }
     });
 
-    return lines.join("\n");
+    return lines.join('\n');
 };
 
 module.exports = PO;

lib/po.js

@@ -1,5 +1,5 @@
-var fs = require('fs'),
-    isArray = require('lodash.isarray');
+var fs = require('fs');
+var isArray = require('lodash.isarray');
 
 function trim(string) {
     return string.replace(/^\s+|\s+$/g, '');
@@ -7,6 +7,7 @@ function trim(string) {
 
 var PO = function () {
     this.comments = [];
+    this.extractedComments = [];
     this.headers = {};
     this.items = [];
 };
@@ -16,21 +17,26 @@ PO.prototype.save = function (filename, callback) {
 };
 
 PO.prototype.toString = function () {
-    var lines = [],
-        that = this;
+    var lines = [];
 
     if (this.comments) {
         this.comments.forEach(function (comment) {
             lines.push('# ' + comment);
         });
     }
+    if (this.extractedComments) {
+        this.extractedComments.forEach(function (comment) {
+            lines.push('#. ' + comment);
+        });
+    }
 
     lines.push('msgid ""');
     lines.push('msgstr ""');
 
     var keys = Object.keys(this.headers);
+    var self = this;
     keys.forEach(function (key) {
-        lines.push('"' + key + ': ' + that.headers[key] + '\\n"');
+        lines.push('"' + key + ': ' + self.headers[key] + '\\n"');
     });
 
     lines.push('');
@@ -40,7 +46,7 @@ PO.prototype.toString = function () {
         lines.push('');
     });
 
-    return lines.join("\n");
+    return lines.join('\n');
 };
 
 PO.load = function (filename, callback) {
@@ -56,10 +62,15 @@ PO.load = function (filename, callback) {
 PO.parse = function (data) {
     //support both unix and windows newline formats.
     data = data.replace(/\r\n/g, '\n');
-    var po = new PO(),
-        sections = data.split(/\n\n/),
-        headers = sections.shift(),
-        lines = sections.join("\n").split(/\n/);
+    var po = new PO();
+    var sections = data.split(/\n\n/);
+    var headers = [sections.shift()];
+    //everything until the first 'msgid ""' is considered header
+    while (headers[headers.length - 1].indexOf('msgid ""') < 0) {
+        headers.push(sections.shift());
+    }
+    headers = headers.join('\n');
+    var lines = sections.join('\n').split(/\n/);
 
     po.headers = {
         'Project-Id-Version': '',
@@ -74,25 +85,44 @@ PO.parse = function (data) {
         'Plural-Forms': '',
     };
 
-    headers.split(/\n/).forEach(function (header) {
-        if (header.match(/^#/)) {
-            po.comments.push(header.replace(/^#\s*/, ''));
+    headers.split(/\n/).reduce(function (acc, line) {
+        if (acc.merge) {
+            //join lines, remove last resp. first "
+            line = acc.pop().slice(0, -1) + line.slice(1);
+            delete acc.merge;
         }
-        if (header.match(/^"/)) {
+        if (/^".*"$/.test(line) && !/^".*\\n"$/.test(line)) {
+            acc.merge = true;
+        }
+        acc.push(line);
+        return acc;
+    }, []).forEach(function (header) {
+        if (header.match(/^#\./)) {
+            po.extractedComments.push(header.replace(/^#\.\s*/, ''));
+        } else if (header.match(/^#/)) {
+            po.comments.push(header.replace(/^#\s*/, ''));
+        } else if (header.match(/^"/)) {
             header = header.trim().replace(/^"/, '').replace(/\\n"$/, '');
-            var p = header.split(/:/),
-                name = p.shift().trim(),
-                value = p.join(':').trim();
+            var p = header.split(/:/);
+            var name = p.shift().trim();
+            var value = p.join(':').trim();
             po.headers[name] = value;
         }
     });
 
-    var item = new PO.Item(),
-        context = null,
-        plural = 0;
+    var item = new PO.Item();
+    var context = null;
+    var plural = 0;
+    var obsoleteCount = 0;
+    var noCommentLineCount = 0;
 
     function finish() {
         if (item.msgid.length > 0) {
+            if (obsoleteCount >= noCommentLineCount) {
+                item.obsolete = true;
+            }
+            obsoleteCount = 0;
+            noCommentLineCount = 0;
             po.items.push(item);
             item = new PO.Item();
         }
@@ -101,61 +131,99 @@ PO.parse = function (data) {
     function extract(string) {
         string = trim(string);
         string = string.replace(/^[^"]*"|"$/g, '');
-        string = string.replace(/\\"/g, '"');
-        string = string.replace(/\\\\/g, '\\');
+        string = string.replace(/\\([abtnvfr'"\\?]|([0-7]{3})|x([0-9a-fA-F]{2}))/g, function (match, esc, oct, hex) {
+            if (oct) {
+                return String.fromCharCode(parseInt(oct, 8));
+            }
+            if (hex) {
+                return String.fromCharCode(parseInt(hex, 16));
+            }
+            switch (esc) {
+                case 'a':
+                    return '\x07';
+                case 'b':
+                    return '\b';
+                case 't':
+                    return '\t';
+                case 'n':
+                    return '\n';
+                case 'v':
+                    return '\v';
+                case 'f':
+                    return '\f';
+                case 'r':
+                    return '\r';
+                default:
+                    return esc;
+            }
+        });
         return string;
     }
 
     while (lines.length > 0) {
-        var line = trim(lines.shift()),
-            add = false;
+        var line = trim(lines.shift());
+        var lineObsolete = false;
+        var add = false;
+
+        if (line.match(/^#\~/)) { // Obsolete item
+            //only remove the obsolte comment mark, here
+            //might be, this is a new item, so
+            //only remember, this line is marked obsolete, count after line is parsed
+            line = trim(line.substring(2));
+            lineObsolete = true;
+        }
+
         if (line.match(/^#:/)) { // Reference
             finish();
             item.references.push(trim(line.replace(/^#:/, '')));
-        }
-        else if (line.match(/^#,/)) { // Flags
+        } else if (line.match(/^#,/)) { // Flags
             finish();
-            var flags = trim(line.replace(/^#,/, '')).split(",");
+            var flags = trim(line.replace(/^#,/, '')).split(',');
             for (var i = 0; i < flags.length; i++) {
                 item.flags[flags[i]] = true;
             }
-        }
-        else if (line.match(/^#/)) { // Comment
+        } else if (line.match(/^#($|\s+)/)) { // Translator comment
             finish();
-            item.comments.push(trim(line.replace(/^#/, '')));
-        }
-        else if (line.match(/^msgid_plural/)) { // Plural form
+            item.comments.push(trim(line.replace(/^#($|\s+)/, '')));
+        } else if (line.match(/^#\./)) { // Extracted comment
+            finish();
+            item.extractedComments.push(trim(line.replace(/^#\./, '')));
+        } else if (line.match(/^msgid_plural/)) { // Plural form
             item.msgid_plural = extract(line);
             context = 'msgid_plural';
-        }
-        else if (line.match(/^msgid/)) { // Original
+            noCommentLineCount++;
+        } else if (line.match(/^msgid/)) { // Original
             finish();
             item.msgid = extract(line);
             context = 'msgid';
-        }
-        else if (line.match(/^msgstr/)) { // Translation
+            noCommentLineCount++;
+        } else if (line.match(/^msgstr/)) { // Translation
             var m = line.match(/^msgstr\[(\d+)\]/);
             plural = m && m[1] ? parseInt(m[1]) : 0;
             item.msgstr[plural] = extract(line);
             context = 'msgstr';
-        }
-        else if (line.match(/^msgctxt/)) { // Context
+            noCommentLineCount++;
+        } else if (line.match(/^msgctxt/)) { // Context
             finish();
             item.msgctxt = extract(line);
-        }
-        else { // Probably multiline string or blank
+            noCommentLineCount++;
+        } else { // Probably multiline string or blank
             if (line.length > 0) {
+                noCommentLineCount++;
                 if (context === 'msgstr') {
                     item.msgstr[plural] += extract(line);
-                }
-                else if (context === 'msgid') {
+                } else if (context === 'msgid') {
                     item.msgid += extract(line);
-                }
-                else if (context === 'msgid_plural') {
+                } else if (context === 'msgid_plural') {
                     item.msgid_plural += extract(line);
                 }
             }
         }
+
+        if (lineObsolete) {
+            // Count obsolete lines for this item
+            obsoleteCount++;
+        }
     }
     finish();
 
@@ -168,57 +236,99 @@ PO.Item = function () {
     this.references = [];
     this.msgid_plural = null;
     this.msgstr = [];
-    this.comments = [];
+    this.comments = []; // translator comments
+    this.extractedComments = [];
     this.flags = {};
+    this.obsolete = false;
 };
 
 PO.Item.prototype.toString = function () {
-    var lines = [],
-        that = this;
+    var lines = [];
+    var self = this;
+
+    // reverse what extract(string) method during PO.parse does
+    var _escape = function (string) {
+        // don't unescape \n, since string can never contain it
+        // since split('\n') is called on it
+        string = string.replace(/[\x07\b\t\v\f\r"\\]/g, function (match) {
+            switch (match) {
+                case '\x07':
+                    return '\\a';
+                case '\b':
+                    return '\\b';
+                case '\t':
+                    return '\\t';
+                case '\v':
+                    return '\\v';
+                case '\f':
+                    return '\\f';
+                case '\r':
+                    return '\\r';
+                default:
+                    return '\\' + match;
+            }
+        });
+        return string;
+    };
 
     var _process = function (keyword, text, i) {
-        var lines = [],
-            parts = text.split(/\n/),
-            index = typeof i !== 'undefined' ? '[' + i + ']' : '';
+        var lines = [];
+        var parts = text.split(/\n/);
+        var index = typeof i !== 'undefined' ? '[' + i + ']' : '';
         if (parts.length > 1) {
             lines.push(keyword + index + ' ""');
             parts.forEach(function (part) {
-                lines.push('"' + part + '"');
+                lines.push('"' + _escape(part) + '"');
             });
-        }
-        else {
-            lines.push(keyword + index + ' "' + text + '"');
+        } else {
+            lines.push(keyword + index + ' "' + _escape(text) + '"');
         }
         return lines;
     };
 
-    if (this.references.length > 0) {
-        this.references.forEach(function (ref) {
-            lines.push('#: ' + ref);
-        });
-    }
+    // https://www.gnu.org/software/gettext/manual/html_node/PO-Files.html
+    // says order is translator-comments, extracted-comments, references, flags
 
-    var flags = Object.keys(this.flags);
+    this.comments.forEach(function (c) {
+        lines.push('# ' + c);
+    });
+
+    this.extractedComments.forEach(function (c) {
+        lines.push('#. ' + c);
+    });
+
+    this.references.forEach(function (ref) {
+        lines.push('#: ' + ref);
+    });
+
+    var flags = Object.keys(this.flags).filter(function (flag) {
+        return !!this.flags[flag];
+    }, this);
     if (flags.length > 0) {
-        lines.push('#, ' + flags.join(","));
+        lines.push('#, ' + flags.join(','));
     }
+    var mkObsolete = this.obsolete ? '#~ ' : '';
 
     ['msgctxt', 'msgid', 'msgid_plural', 'msgstr'].forEach(function (keyword) {
-        var text = that[keyword];
+        var text = self[keyword];
         if (text != null) {
             if (isArray(text) && text.length > 1) {
                 text.forEach(function (t, i) {
-                    lines = lines.concat(_process(keyword, t, i));
+                    lines = lines.concat(mkObsolete + _process(keyword, t, i));
                 });
-            }
-            else {
+            } else {
                 text = isArray(text) ? text.join() : text;
-                lines = lines.concat(_process(keyword, text));
+                var processed = _process(keyword, text);
+                //handle \n in single-line texts (can not be handled in _escape)
+                for (var i = 1; i < processed.length - 1; i++) {
+                    processed[i] = processed[i].slice(0, -1) + '\\n"';
+                }
+                lines = lines.concat(mkObsolete + processed.join('\n' + mkObsolete));
             }
         }
     });
 
-    return lines.join("\n");
+    return lines.join('\n');
 };
 
 module.exports = PO;

package.json

@@ -1,14 +1,18 @@
 {
   "name": "pofile",
   "description": "Parse and serialize Gettext PO files.",
-  "version": "0.2.4",
+  "version": "1.0.1",
   "author": {
     "name": "Ruben Vermeersch",
     "email": "ruben@savanne.be",
     "url": "http://savanne.be/"
   },
   "contributors": [
-    "Mike Holly"
+    "Eyal Lewinsohn",
+    "Gabe Gorelick",
+    "Julian Bäume",
+    "Mike Holly",
+    "Sander Houttekier"
   ],
   "homepage": "http://github.com/rubenv/pofile",
   "repository": {
@@ -24,21 +28,23 @@
     "po"
   ],
   "scripts": {
-    "test": "grunt test"
+    "test": "grunt test",
+    "prepublish": "grunt build"
   },
   "directories": {
     "test": "test"
   },
   "devDependencies": {
-    "grunt": "~0.4.2",
-    "grunt-contrib-watch": "~0.5.3",
-    "grunt-contrib-jshint": "~0.7.2",
-    "grunt-mocha-cli": "~1.4.0",
-    "grunt-contrib-uglify": "~0.2.7",
     "browserify": "~3.11.1",
+    "grunt": "~0.4.2",
     "grunt-browserify": "~1.3.0",
+    "grunt-bump": "0.0.13",
     "grunt-contrib-clean": "~0.5.0",
-    "grunt-bump": "0.0.13"
+    "grunt-contrib-jshint": "~0.7.2",
+    "grunt-contrib-uglify": "~0.2.7",
+    "grunt-contrib-watch": "~0.5.3",
+    "grunt-jscs-checker": "^0.5.1",
+    "grunt-mocha-cli": "~1.4.0"
   },
   "dependencies": {
     "lodash.isarray": "~2.4.1"

test/fixtures/big.po

@@ -1,4 +1,5 @@
 # French translation of Link (6.x-2.9)
+
 # Copyright (c) 2011 by the French translation team
 #
 msgid ""

test/fixtures/c-strings.po

@@ -0,0 +1,59 @@
+# French translation of Link (6.x-2.9)
+# Copyright (c) 2011 by the French translation team
+msgid ""
+msgstr ""
+"Project-Id-Version: Link (6.x-2.9)\n"
+"Report-Msgid-Bugs-To: \n"
+"POT-Creation-Date: 2011-12-31 23:39+0000\n"
+"PO-Revision-Date: 2013-12-17 14:59+0100\n"
+"Last-Translator: Ruben Vermeersch <ruben@rocketeer.be>\n"
+"Language: fr\n"
+"Language-Team: French\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Plural-Forms: nplurals=2; plural=(n > 1);\n"
+"MIME-Version: 1.0\n"
+"X-Generator: Poedit 1.6.2\n"
+
+msgid "The name field must not contain characters like \" or \\"
+msgstr ""
+
+# possibility to reorder items depending on locale
+#. Format of addresses
+#. %1$s is the street
+#. %2$s is the postal code
+#. %3$s is the city
+#. %4$s is the state
+#. %5$s is the country
+msgid ""
+"%1$s\n"
+"%2$s %3$s\n"
+"%4$s\n"
+"%5$s"
+msgstr ""
+
+# "i18"ned code
+#. used in <pre> environment, so don't remove any control sequences
+msgid ""
+"define('some/test/module', function () {\n"
+"\t'use strict';\n"
+"\treturn {};\n"
+"});\n"
+""
+msgstr ""
+"define('random/test/file', function () {\n"
+"\t'use strict';\n"
+"\treturn {};\n"
+"});\n"
+""
+
+# all one-letter escape characters
+# be aware, that \a, \b, \v, \f and \r should not be used
+# in i18ned messages (according to gettext tools)
+# however, they should be properly parsed, anyway
+msgid ""
+"\a\b\t\n"
+"\v\f\r"
+msgstr ""
+"\a\b\t\n"
+"\v\f\r"

test/fixtures/comment.po

@@ -1,6 +1,7 @@
 # French translation of Link (6.x-2.9)
 # Copyright (c) 2011 by the French translation team
 #
+#. extracted from test
 msgid ""
 msgstr ""
 "Project-Id-Version: Link (6.x-2.9)\n"
@@ -15,6 +16,15 @@ msgstr ""
 "Language: fr\n"
 "X-Generator: Poedit 1.6.2\n"
 
-# Comment
+# Translator comment
+#. Extracted comment
 msgid "Title, as plain text"
 msgstr "Attribut title, en tant que texte brut"
+
+#
+#.
+#:
+#, fuzzy
+msgid "Empty comment"
+msgstr "Empty"
+

test/fixtures/commented.po

@@ -0,0 +1,33 @@
+msgid ""
+msgstr ""
+"Project-Id-Version: Test\n"
+"POT-Creation-Date: \n"
+"PO-Revision-Date: 2014-02-17 14:11+0100\n"
+"Last-Translator: Ruben Vermeersch <ruben@rocketeer.be>\n"
+"Language-Team: \n"
+"Language: nl\n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+"Plural-Forms: nplurals=2; plural=(n != 1);\n"
+"X-Generator: Poedit 1.6.4\n"
+"X-Poedit-SourceCharset: UTF-8\n"
+"X-POOTLE-MTIME: 1390921449.000000\n"
+
+
+#: .tmp/ui/settings/views/console-modal.html
+msgid "{{dataLoader.data.length}} results"
+msgstr "{{dataLoader.data.length}} resultaten"
+
+#~ msgid "Add order"
+#~ msgstr "Order toevoegen"
+
+#~ # commented obsolete item
+#~ #, fuzzy
+#~ msgid "Commented item"
+#~ msgstr "not sure"
+
+# commented obsolete item
+#, fuzzy
+#~ msgid "Second commented item"
+#~ msgstr "also not sure"

test/fixtures/multi-line.po

@@ -1,6 +1,8 @@
 # French translation of Link (6.x-2.9)
 # Copyright (c) 2011 by the French translation team
 #
+## Plural-Forms by polish translation team to demonstrate multi-line ##
+#
 msgid ""
 msgstr ""
 "Project-Id-Version: Link (6.x-2.9)\n"
@@ -10,7 +12,8 @@ msgstr ""
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=UTF-8\n"
 "Content-Transfer-Encoding: 8bit\n"
-"Plural-Forms: nplurals=2; plural=(n > 1);\n"
+"Plural-Forms: nplurals=3; plural=n==1 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 "
+"|| n%100>=20) ? 1 : 2;\n"
 "Last-Translator: Ruben Vermeersch <ruben@rocketeer.be>\n"
 "Language: fr\n"
 "X-Generator: Poedit 1.6.2\n"

test/fixtures/reference.po

@@ -24,3 +24,7 @@ msgstr "Attribut title, en tant que texte brut"
 #: b
 msgid "X"
 msgstr "Y"
+
+#: standard input:12 standard input:17
+msgid "Z"
+msgstr "ZZ"

test/parse.js

@@ -7,48 +7,95 @@ describe('Parse', function () {
         var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/big.po', 'utf8'));
         assert.notEqual(po, null);
         assert.equal(po.items.length, 69);
-        
+
         var item = po.items[0];
-        assert.equal(item.msgid, "Title");
-        assert.equal(item.msgstr, "Titre");
+        assert.equal(item.msgid, 'Title');
+        assert.equal(item.msgstr, 'Titre');
     });
 
     it('Handles multi-line strings', function () {
         var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/multi-line.po', 'utf8'));
         assert.notEqual(po, null);
         assert.equal(po.items.length, 1);
-        
+
         var item = po.items[0];
-        assert.equal(item.msgid, "The following placeholder tokens can be used in both paths and titles. When used in a path or title, they will be replaced with the appropriate values.");
-        assert.equal(item.msgstr, "Les ébauches de jetons suivantes peuvent être utilisées à la fois dans les chemins et dans les titres. Lorsqu'elles sont utilisées dans un chemin ou un titre, elles seront remplacées par les valeurs appropriées.");
+        assert.equal(item.msgid, 'The following placeholder tokens can be used in both paths and titles. When used in a path or title, they will be replaced with the appropriate values.');
+        assert.equal(item.msgstr, 'Les ébauches de jetons suivantes peuvent être utilisées à la fois dans les chemins et dans les titres. Lorsqu\'elles sont utilisées dans un chemin ou un titre, elles seront remplacées par les valeurs appropriées.');
     });
 
-    it('Handles string comments', function () {
-        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/comment.po', 'utf8'));
+    it('Handles multi-line headers', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/multi-line.po', 'utf8'));
         assert.notEqual(po, null);
         assert.equal(po.items.length, 1);
-        
-        var item = po.items[0];
-        assert.equal(item.msgid, "Title, as plain text");
-        assert.equal(item.msgstr, "Attribut title, en tant que texte brut");
-        assert.deepEqual(item.comments, ["Comment"]);
+
+        assert.equal(po.headers['Plural-Forms'], 'nplurals=3; plural=n==1 ? 0 : n%10>=2 && n%10<=4 && (n%100<10 || n%100>=20) ? 1 : 2;');
     });
 
-    it('Handles string references', function () {
-        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/reference.po', 'utf8'));
+    it('Handle empty comments', function (done) {
+        PO.load(__dirname + '/fixtures/comment.po', function (err, po) {
+            assert.equal(err, null);
+
+            var item = po.items[1];
+            assert.equal(item.msgid, 'Empty comment');
+            assert.equal(item.msgstr, 'Empty');
+            assert.deepEqual(item.comments, ['']);
+            assert.deepEqual(item.extractedComments, ['']);
+            assert.deepEqual(item.references, ['']);
+            done();
+        });
+    });
+
+    it('Handles translator comments', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/comment.po', 'utf8'));
         assert.notEqual(po, null);
         assert.equal(po.items.length, 2);
-        
+
         var item = po.items[0];
-        assert.equal(item.msgid, "Title, as plain text");
-        assert.equal(item.msgstr, "Attribut title, en tant que texte brut");
-        assert.deepEqual(item.comments, ["Comment"]);
-        assert.deepEqual(item.references, [".tmp/crm/controllers/map.js"]);
-        
-        item = po.items[1];
-        assert.equal(item.msgid, "X");
-        assert.equal(item.msgstr, "Y");
-        assert.deepEqual(item.references, ["a", "b"]);
+        assert.equal(item.msgid, 'Title, as plain text');
+        assert.equal(item.msgstr, 'Attribut title, en tant que texte brut');
+        assert.deepEqual(item.comments, ['Translator comment']);
+    });
+
+    it('Handles extracted comments', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/comment.po', 'utf8'));
+        assert.notEqual(po, null);
+        assert.equal(po.items.length, 2);
+
+        assert.equal(po.extractedComments.length, 1);
+        assert.equal(po.extractedComments[0], 'extracted from test');
+
+        var item = po.items[0];
+        assert.equal(item.msgid, 'Title, as plain text');
+        assert.equal(item.msgstr, 'Attribut title, en tant que texte brut');
+        assert.deepEqual(item.extractedComments, ['Extracted comment']);
+    });
+
+    describe('Handles string references', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/reference.po', 'utf8'));
+        assert.notEqual(po, null);
+        assert.equal(po.items.length, 3);
+
+        it('in simple cases', function () {
+            var item = po.items[0];
+            assert.equal(item.msgid, 'Title, as plain text');
+            assert.equal(item.msgstr, 'Attribut title, en tant que texte brut');
+            assert.deepEqual(item.comments, ['Comment']);
+            assert.deepEqual(item.references, ['.tmp/crm/controllers/map.js']);
+        });
+
+        it('with two different references', function () {
+            var item = po.items[1];
+            assert.equal(item.msgid, 'X');
+            assert.equal(item.msgstr, 'Y');
+            assert.deepEqual(item.references, ['a', 'b']);
+        });
+
+        it('and does not process reference items', function () {
+            var item = po.items[2];
+            assert.equal(item.msgid, 'Z');
+            assert.equal(item.msgstr, 'ZZ');
+            assert.deepEqual(item.references, ['standard input:12 standard input:17']);
+        });
     });
 
     it('Parses flags', function () {
@@ -57,8 +104,8 @@ describe('Parse', function () {
         assert.equal(po.items.length, 1);
 
         var item = po.items[0];
-        assert.equal(item.msgid, "Sources");
-        assert.equal(item.msgstr, "Source");
+        assert.equal(item.msgid, 'Sources');
+        assert.equal(item.msgstr, 'Source');
         assert.notEqual(item.flags, null);
         assert.equal(item.flags.fuzzy, true);
     });
@@ -73,4 +120,56 @@ describe('Parse', function () {
         assert.equal(ambiguousItems[0].msgctxt, 'folder display');
         assert.equal(ambiguousItems[1].msgctxt, 'folder action');
     });
+
+    it('Handles obsolete items', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/commented.po', 'utf8'));
+
+        assert.equal(po.items.length, 4);
+        var item = po.items[0];
+        assert.equal(item.obsolete, false);
+        assert.equal(item.msgid, '{{dataLoader.data.length}} results');
+        assert.equal(item.msgstr, '{{dataLoader.data.length}} resultaten');
+
+        item = po.items[1];
+        assert.equal(item.obsolete, true);
+        assert.equal(item.msgid, 'Add order');
+        assert.equal(item.msgstr, 'Order toevoegen');
+
+        item = po.items[2];
+        assert.equal(item.obsolete, true);
+        assert.equal(item.msgid, 'Commented item');
+        assert.equal(item.msgstr, 'not sure');
+
+        item = po.items[3];
+        assert.equal(item.obsolete, true);
+        assert.equal(item.msgid, 'Second commented item');
+        assert.equal(item.msgstr, 'also not sure');
+    });
+
+    describe('C-Strings', function () {
+        var po = PO.parse(fs.readFileSync(__dirname + '/fixtures/c-strings.po', 'utf8'));
+        it('should parse the c-strings.po file', function () {
+            assert.notEqual(po, null);
+        });
+
+        it('should extract strings containing " and \\ characters', function () {
+            var items = po.items.filter(function (item) {
+                return (/^The name field must not contain/).test(item.msgid);
+            });
+            assert.equal(items[0].msgid, 'The name field must not contain characters like " or \\');
+        });
+
+        it('should handle \\n characters', function () {
+            var item = po.items[1];
+            assert.equal(item.msgid, '%1$s\n%2$s %3$s\n%4$s\n%5$s');
+        });
+
+        it('should handle \\t characters', function () {
+            var item = po.items[2];
+            assert.equal(item.msgid, 'define(\'some/test/module\', function () {\n' +
+                '\t\'use strict\';\n' +
+                '\treturn {};\n' +
+                '});\n');
+        });
+    });
 });

test/write.js

@@ -3,7 +3,7 @@ var fs = require('fs');
 var PO = require('..');
 
 function assertHasLine(str, line) {
-    var lines = str.split("\n");
+    var lines = str.split('\n');
     var found = false;
 
     for (var i = 0; i < lines.length; i++) {
@@ -13,7 +13,21 @@ function assertHasLine(str, line) {
         }
     }
 
-    assert(found, "Could not find line: " + line);
+    assert(found, 'Could not find line: ' + line);
+}
+
+function assertDoesntHaveLine(str, line) {
+    var lines = str.split('\n');
+    var found = false;
+
+    for (var i = 0; i < lines.length; i++) {
+        if (lines[i].trim() === line) {
+            found = true;
+            break;
+        }
+    }
+
+    assert(!found, 'Shouldn\'t have line: ' + line);
 }
 
 describe('Write', function () {
@@ -21,21 +35,105 @@ describe('Write', function () {
         var input = fs.readFileSync(__dirname + '/fixtures/fuzzy.po', 'utf8');
         var po = PO.parse(input);
         var str = po.toString();
-        assertHasLine(str, "#, fuzzy");
+        assertHasLine(str, '#, fuzzy');
+    });
+
+    it('write flags only when true', function () {
+        var input = fs.readFileSync(__dirname + '/fixtures/fuzzy.po', 'utf8');
+        var po = PO.parse(input);
+
+        // Flip flag
+        po.items[0].flags.fuzzy = false;
+
+        var str = po.toString();
+        assertDoesntHaveLine(str, '#, fuzzy');
     });
 
     it('write msgid', function () {
         var input = fs.readFileSync(__dirname + '/fixtures/fuzzy.po', 'utf8');
         var po = PO.parse(input);
         var str = po.toString();
-        assertHasLine(str, "msgid \"Sources\"");
+        assertHasLine(str, 'msgid "Sources"');
     });
 
     it('write msgstr', function () {
         var input = fs.readFileSync(__dirname + '/fixtures/fuzzy.po', 'utf8');
         var po = PO.parse(input);
         var str = po.toString();
-        assertHasLine(str, "msgstr \"Source\"");
+        assertHasLine(str, 'msgstr "Source"');
+    });
+
+    it('write translator comment', function () {
+        var input = fs.readFileSync(__dirname + '/fixtures/comment.po', 'utf8');
+        var po = PO.parse(input);
+        var str = po.toString();
+        assertHasLine(str, '# Translator comment');
+    });
+
+    it('write extracted comment', function () {
+        var input = fs.readFileSync(__dirname + '/fixtures/comment.po', 'utf8');
+        var po = PO.parse(input);
+        var str = po.toString();
+        assertHasLine(str, '#. extracted from test');
+        assertHasLine(str, '#. Extracted comment');
+    });
+
+    it('write obsolete items', function () {
+        var input = fs.readFileSync(__dirname + '/fixtures/commented.po', 'utf8');
+        var po = PO.parse(input);
+        var str = po.toString();
+
+        assertHasLine(str, '#~ msgid "Add order"');
+        assertHasLine(str, '#~ msgstr "Order toevoegen"');
+    });
+
+    it('write obsolete items with comment', function () {
+        var input = fs.readFileSync(__dirname + '/fixtures/commented.po', 'utf8');
+        var po = PO.parse(input);
+        var str = po.toString();
+
+        //this is what msgcat tool of gettext does: don't print #~ for comments
+        assertHasLine(str, '# commented obsolete item');
+        assertHasLine(str, '#, fuzzy');
+
+        //items made obsolete by commenting every keyword with #~
+        assertHasLine(str, '#~ msgid "Commented item"');
+        assertHasLine(str, '#~ msgstr "not sure"');
+        assertHasLine(str, '#~ msgid "Second commented item"');
+        assertHasLine(str, '#~ msgstr "also not sure"');
+    });
+
+    describe('C-Strings', function () {
+        it('should escape "', function () {
+            var item = new PO.Item();
+
+            item.msgid = '" should be written escaped';
+            assertHasLine(item.toString(), 'msgid "\\" should be written escaped"');
+        });
+
+        it('shoudl escape \\', function () {
+            var item = new PO.Item();
+
+            item.msgid = '\\ should be written escaped';
+            assertHasLine(item.toString(), 'msgid "\\\\ should be written escaped"');
+        });
+
+        it('should escape \\n', function () {
+            var item = new PO.Item();
+
+            item.msgid = '\n should be written escaped';
+            assertHasLine(item.toString(), 'msgid ""');
+            assertHasLine(item.toString(), '"\\n"');
+            assertHasLine(item.toString(), '" should be written escaped"');
+        });
+
+        it('should write identical file after parsing a file', function () {
+            var input = fs.readFileSync(__dirname + '/fixtures/c-strings.po', 'utf8');
+            var po = PO.parse(input);
+            var str = po.toString();
+
+            assert.equal(str, input);
+        });
     });
 
     describe('msgctxt', function () {