From 6f0f7f634c26569aa5514419562eac0b760f6dca Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 10:19:25 +0000 Subject: [PATCH 01/14] Changing file state throughout save process to track where saving is becoming stuck --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index bac224fd..8682cce9 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#b55229eb75", + "c9.ide.collab": "#b8d55bf047", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 3b0aeacf88e8498e25a990ff685f9e7cf900cdf5 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 10:24:07 +0000 Subject: [PATCH 02/14] Don't setup saveWatchDog in save as it will always timeout if state is not IDLE --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index 8682cce9..eae53bd5 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#b8d55bf047", + "c9.ide.collab": "#5bd4bc994e", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 9afcca6e94687589dcbec97688d512375dcd1238 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 10:38:05 +0000 Subject: [PATCH 03/14] Send error before setting state back to IDLE --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index eae53bd5..55624714 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#5bd4bc994e", + "c9.ide.collab": "#9e2f7dbac2", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 5b6b9266ac3aa6fb809458cf1415787178f8dcb9 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 10:41:04 +0000 Subject: [PATCH 04/14] Don't set IDLE too early --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index 55624714..c44eec06 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#9e2f7dbac2", + "c9.ide.collab": "#eb7ed1f00e", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From e22436350f9c11e37dda48170b212210fc1a3e35 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 11:01:32 +0000 Subject: [PATCH 05/14] Changing saveState instead of state now --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index c44eec06..a7ce9dec 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#eb7ed1f00e", + "c9.ide.collab": "#19594028b7", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 3225ca94ac9163a815bb4d774cb1f366df5c85e5 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 11:08:32 +0000 Subject: [PATCH 06/14] SaveStateDebugging yay --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index a7ce9dec..25ba42af 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#19594028b7", + "c9.ide.collab": "#04d812d8d3", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 0bcd25830cd1613dff7dbee20545419c5c116715 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 14:01:20 +0000 Subject: [PATCH 07/14] Using fallback save if document state is not idle --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index 25ba42af..f5ed93f6 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#04d812d8d3", + "c9.ide.collab": "#be9949cd7f", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 0f74b9ea3b14309c3da611124939d7fcaca5475d Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 14:34:25 +0000 Subject: [PATCH 08/14] Using old logic but a new warning message for file saves actually timing out vs those done when disconnected --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index f5ed93f6..d2228c9a 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#be9949cd7f", + "c9.ide.collab": "#38f97e655f", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From a322679514636dae37605551378fba30a25e0184 Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 14:35:19 +0000 Subject: [PATCH 09/14] Adding stateWhenSaveCalled for debugging purposes --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index d2228c9a..f36f44b6 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#38f97e655f", + "c9.ide.collab": "#1213837934", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 9c97257dcda20315f85c46566ff46831cc7df66b Mon Sep 17 00:00:00 2001 From: Tim Robinson Date: Tue, 30 Jun 2015 14:39:05 +0000 Subject: [PATCH 10/14] style --- package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/package.json b/package.json index f36f44b6..a0392911 100644 --- a/package.json +++ b/package.json @@ -67,7 +67,7 @@ "c9.ide.language.javascript.tern": "#2b0bb024da", "c9.ide.language.javascript.infer": "#cfec494a3c", "c9.ide.language.jsonalyzer": "#ba3e0d298c", - "c9.ide.collab": "#1213837934", + "c9.ide.collab": "#cb76550803", "c9.ide.local": "#a9703b630c", "c9.ide.find": "#6cc6d3379d", "c9.ide.find.infiles": "#72582de3cd", From 2aac81b7e7b5879a0fbcf2bab8c544dc1fa5f92e Mon Sep 17 00:00:00 2001 From: Lennart Kats Date: Fri, 3 Jul 2015 16:59:18 +0200 Subject: [PATCH 11/14] Revert "Escape only invalid character sequences in reliable socket" --- .../connect.render.ejs/render-ejs.js | 2 +- node_modules/kaefer/lib/reliable_socket.js | 18 +++--------------- node_modules/kaefer/lib/version.js | 2 +- 3 files changed, 5 insertions(+), 17 deletions(-) diff --git a/node_modules/connect-architect/connect.render.ejs/render-ejs.js b/node_modules/connect-architect/connect.render.ejs/render-ejs.js index 5c25e970..9a544416 100644 --- a/node_modules/connect-architect/connect.render.ejs/render-ejs.js +++ b/node_modules/connect-architect/connect.render.ejs/render-ejs.js @@ -7,7 +7,7 @@ module.exports = function(options, imports, register) { imports["connect.render"].registerEngine("ejs", createView); ejs.filters.JSONToJS = function(obj, indent) { - return JSON.stringify(obj, null, indent).replace(/<\/?script|[\u2028\u2029\ud800-\uDFFF\ufeff]/ig, function(a) { + return JSON.stringify(obj, null, indent).replace(/<\/?script|[\u2028\u2029]/ig, function(a) { var h = a.charCodeAt(0).toString(16); return (h.length == 2 ? "\\x" : "\\u") + h + a.substr(1); }); diff --git a/node_modules/kaefer/lib/reliable_socket.js b/node_modules/kaefer/lib/reliable_socket.js index ddb2f1f9..9747de00 100644 --- a/node_modules/kaefer/lib/reliable_socket.js +++ b/node_modules/kaefer/lib/reliable_socket.js @@ -64,22 +64,10 @@ Object.defineProperty(ReliableSocket.prototype, "readyState", { } }); -function utf8escape(str) { - return str.replace(/[\ud799-\uDFFF]/g, function(x) { - return "\ud799" + String.fromCharCode(x.charCodeAt(0) - 0xd700); - }); -} - -function utf8unescape(str) { - return str.replace(/\ud799./g, function(x) { - return String.fromCharCode(x.charCodeAt(1) + 0xd700); - }); -} - ReliableSocket.prototype.onMessage = function(msg) { if (typeof msg == "string") { try { - msg = JSON.parse(utf8unescape(msg)); + msg = JSON.parse(unescape(msg)); } catch(e) {} } this.debug && console.log("on message", msg, this.seq); @@ -240,7 +228,7 @@ ReliableSocket.prototype._cancelDelayedAck = function() { ReliableSocket.prototype._ack = function() { if (this.socket.readyState == "open") { this.debug && console.log("send ack", this.recId); - this.socket.send(utf8escape(JSON.stringify({ + this.socket.send(encodeURI(JSON.stringify({ ack: this.recId }))); } @@ -336,7 +324,7 @@ ReliableSocket.prototype._sendMessage = function(data, type) { that._updateRetransmissionTimeout(Date.now() - msg.ts); }, serialize: function() { - return utf8escape(JSON.stringify({ + return escape(JSON.stringify({ ack: that.recId, seq: msg.seq, d: data, diff --git a/node_modules/kaefer/lib/version.js b/node_modules/kaefer/lib/version.js index 9659ae0f..0b3793ea 100644 --- a/node_modules/kaefer/lib/version.js +++ b/node_modules/kaefer/lib/version.js @@ -2,6 +2,6 @@ define(function(require, exports, module) { // on each backwards incompatible protocol change the version number must be // increased -exports.protocol = 10; +exports.protocol = 9; }); \ No newline at end of file From f1c157530223f8cbd4ec09f33fe496e0aeb975c8 Mon Sep 17 00:00:00 2001 From: Lennart Kats Date: Fri, 3 Jul 2015 16:59:39 +0200 Subject: [PATCH 12/14] Revert "Revert "Escape only invalid character sequences in reliable socket"" --- .../connect.render.ejs/render-ejs.js | 2 +- node_modules/kaefer/lib/reliable_socket.js | 18 +++++++++++++++--- node_modules/kaefer/lib/version.js | 2 +- 3 files changed, 17 insertions(+), 5 deletions(-) diff --git a/node_modules/connect-architect/connect.render.ejs/render-ejs.js b/node_modules/connect-architect/connect.render.ejs/render-ejs.js index 9a544416..5c25e970 100644 --- a/node_modules/connect-architect/connect.render.ejs/render-ejs.js +++ b/node_modules/connect-architect/connect.render.ejs/render-ejs.js @@ -7,7 +7,7 @@ module.exports = function(options, imports, register) { imports["connect.render"].registerEngine("ejs", createView); ejs.filters.JSONToJS = function(obj, indent) { - return JSON.stringify(obj, null, indent).replace(/<\/?script|[\u2028\u2029]/ig, function(a) { + return JSON.stringify(obj, null, indent).replace(/<\/?script|[\u2028\u2029\ud800-\uDFFF\ufeff]/ig, function(a) { var h = a.charCodeAt(0).toString(16); return (h.length == 2 ? "\\x" : "\\u") + h + a.substr(1); }); diff --git a/node_modules/kaefer/lib/reliable_socket.js b/node_modules/kaefer/lib/reliable_socket.js index 9747de00..ddb2f1f9 100644 --- a/node_modules/kaefer/lib/reliable_socket.js +++ b/node_modules/kaefer/lib/reliable_socket.js @@ -64,10 +64,22 @@ Object.defineProperty(ReliableSocket.prototype, "readyState", { } }); +function utf8escape(str) { + return str.replace(/[\ud799-\uDFFF]/g, function(x) { + return "\ud799" + String.fromCharCode(x.charCodeAt(0) - 0xd700); + }); +} + +function utf8unescape(str) { + return str.replace(/\ud799./g, function(x) { + return String.fromCharCode(x.charCodeAt(1) + 0xd700); + }); +} + ReliableSocket.prototype.onMessage = function(msg) { if (typeof msg == "string") { try { - msg = JSON.parse(unescape(msg)); + msg = JSON.parse(utf8unescape(msg)); } catch(e) {} } this.debug && console.log("on message", msg, this.seq); @@ -228,7 +240,7 @@ ReliableSocket.prototype._cancelDelayedAck = function() { ReliableSocket.prototype._ack = function() { if (this.socket.readyState == "open") { this.debug && console.log("send ack", this.recId); - this.socket.send(encodeURI(JSON.stringify({ + this.socket.send(utf8escape(JSON.stringify({ ack: this.recId }))); } @@ -324,7 +336,7 @@ ReliableSocket.prototype._sendMessage = function(data, type) { that._updateRetransmissionTimeout(Date.now() - msg.ts); }, serialize: function() { - return escape(JSON.stringify({ + return utf8escape(JSON.stringify({ ack: that.recId, seq: msg.seq, d: data, diff --git a/node_modules/kaefer/lib/version.js b/node_modules/kaefer/lib/version.js index 0b3793ea..9659ae0f 100644 --- a/node_modules/kaefer/lib/version.js +++ b/node_modules/kaefer/lib/version.js @@ -2,6 +2,6 @@ define(function(require, exports, module) { // on each backwards incompatible protocol change the version number must be // increased -exports.protocol = 9; +exports.protocol = 10; }); \ No newline at end of file From 8eae151d7b4535b22f9d401d28bbf83fcc38fc40 Mon Sep 17 00:00:00 2001 From: Ruben Daniels Date: Fri, 3 Jul 2015 19:50:46 +0000 Subject: [PATCH 13/14] Tweaks to c9 list command --- plugins/c9.cli.publish/list.js | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/plugins/c9.cli.publish/list.js b/plugins/c9.cli.publish/list.js index 730ef4dc..82446bca 100644 --- a/plugins/c9.cli.publish/list.js +++ b/plugins/c9.cli.publish/list.js @@ -86,9 +86,10 @@ define(function(require, exports, module) { list.forEach(function(item){ console.log( pad(item.name, max[0] + PADDING), - pad(item.description.split(".")[0], max[1] + PADDING), - LIGHTBlUE + pad("https://c9.io/profile/packages/" + item.name, max[2] + PADDING) + RESETCOLOR, - item.website || item.repository.url); // do not pad last item + item.description.split(".")[0].replace(/[\r\n]/g, "")); + // pad(item.description.split(".")[0].replace(/[\r\n]/g, "-"), max[1] + PADDING)); + // LIGHTBlUE + pad("https://c9.io/packages/" + item.name, max[2] + PADDING) + RESETCOLOR, + // item.website || item.repository.url); // do not pad last item }); return callback(null, list); } From b862cf750e11ffe718e3346b12e2dec77d34c2e0 Mon Sep 17 00:00:00 2001 From: nightwing Date: Sat, 4 Jul 2015 16:57:35 +0400 Subject: [PATCH 14/14] fix +3385: fullwidth characters are not handled by libterm --- plugins/c9.ide.terminal/aceterm/libterm.js | 28 +- plugins/c9.ide.terminal/aceterm/wc.js | 416 +++++++++++++++++++++ 2 files changed, 440 insertions(+), 4 deletions(-) create mode 100644 plugins/c9.ide.terminal/aceterm/wc.js diff --git a/plugins/c9.ide.terminal/aceterm/libterm.js b/plugins/c9.ide.terminal/aceterm/libterm.js index 3a832c8e..1e1072d6 100644 --- a/plugins/c9.ide.terminal/aceterm/libterm.js +++ b/plugins/c9.ide.terminal/aceterm/libterm.js @@ -26,6 +26,7 @@ define(function(require, exports, module) { */ var EventEmitter = require("events").EventEmitter; +var wc = require("./wc"); var normal = 0 , escaped = 1 @@ -455,10 +456,29 @@ Terminal.prototype.writeInternal = function(data) {//TODO optimize lines insertY = lines.length - 1; } - if (!this.insertMode) - lines[insertY][this.x] = [this.curAttr, ch]; - else - lines[insertY].splice(this.x, 0, [this.curAttr, ch]); + var width = ch > "\x7f" ? wc.charWidth(ch.charCodeAt(0)) : 1; + line = lines[insertY]; + switch (width) { + case 1: + if (!this.insertMode) + line[this.x] = [this.curAttr, ch]; + else + line[insertY].splice(this.x, 0, [this.curAttr, ch]); + break; + case 0: + if (this.x > 0) this.x--; + line[this.x] = [this.curAttr, line[this.x][1] + ch]; + break; + case 2: + if (!this.insertMode) { + line[this.x] = [this.curAttr, ch]; + line[this.x + 1] = [this.curAttr, ""]; + } else { + line[insertY].splice(this.x, 0, [this.curAttr, ch], [this.curAttr, ""]); + } + this.x++; + break; + } this.x++; this.updateRange(this.y); diff --git a/plugins/c9.ide.terminal/aceterm/wc.js b/plugins/c9.ide.terminal/aceterm/wc.js new file mode 100644 index 00000000..d476804a --- /dev/null +++ b/plugins/c9.ide.terminal/aceterm/wc.js @@ -0,0 +1,416 @@ +define(function(require, exports, module) { +'use strict'; + +/** + * This JavaScript library is ported from the wcwidth.js module of node.js. + * The original implementation can be found at: + * https://npmjs.org/package/wcwidth.js + */ + +/** + * JavaScript porting of Markus Kuhn's wcwidth() implementation + * + * The following explanation comes from the original C implementation: + * + * This is an implementation of wcwidth() and wcswidth() (defined in + * IEEE Std 1002.1-2001) for Unicode. + * + * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html + * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html + * + * In fixed-width output devices, Latin characters all occupy a single + * "cell" position of equal width, whereas ideographic CJK characters + * occupy two such cells. Interoperability between terminal-line + * applications and (teletype-style) character terminals using the + * UTF-8 encoding requires agreement on which character should advance + * the cursor by how many cell positions. No established formal + * standards exist at present on which Unicode character shall occupy + * how many cell positions on character terminals. These routines are + * a first attempt of defining such behavior based on simple rules + * applied to data provided by the Unicode Consortium. + * + * For some graphical characters, the Unicode standard explicitly + * defines a character-cell width via the definition of the East Asian + * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes. + * In all these cases, there is no ambiguity about which width a + * terminal shall use. For characters in the East Asian Ambiguous (A) + * class, the width choice depends purely on a preference of backward + * compatibility with either historic CJK or Western practice. + * Choosing single-width for these characters is easy to justify as + * the appropriate long-term solution, as the CJK practice of + * displaying these characters as double-width comes from historic + * implementation simplicity (8-bit encoded characters were displayed + * single-width and 16-bit ones double-width, even for Greek, + * Cyrillic, etc.) and not any typographic considerations. + * + * Much less clear is the choice of width for the Not East Asian + * (Neutral) class. Existing practice does not dictate a width for any + * of these characters. It would nevertheless make sense + * typographically to allocate two character cells to characters such + * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be + * represented adequately with a single-width glyph. The following + * routines at present merely assign a single-cell width to all + * neutral characters, in the interest of simplicity. This is not + * entirely satisfactory and should be reconsidered before + * establishing a formal standard in lib.wc area. At the moment, the + * decision which Not East Asian (Neutral) characters should be + * represented by double-width glyphs cannot yet be answered by + * applying a simple rule from the Unicode database content. Setting + * up a proper standard for the behavior of UTF-8 character terminals + * will require a careful analysis not only of each Unicode character, + * but also of each presentation form, something the author of these + * routines has avoided to do so far. + * + * http://www.unicode.org/unicode/reports/tr11/ + * + * Markus Kuhn -- 2007-05-26 (Unicode 5.0) + * + * Permission to use, copy, modify, and distribute lib.wc software + * for any purpose and without fee is hereby granted. The author + * disclaims all warranties with regard to lib.wc software. + * + * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c + */ + +/** + * The following function defines the column width of an ISO 10646 character + * as follows: + * + * - The null character (U+0000) has a column width of 0. + * - Other C0/C1 control characters and DEL will lead to a return value of -1. + * - Non-spacing and enclosing combining characters (general category code Mn + * or Me in the Unicode database) have a column width of 0. + * - SOFT HYPHEN (U+00AD) has a column width of 1. + * - Other format characters (general category code Cf in the Unicode database) + * and ZERO WIDTH SPACE (U+200B) have a column width of 0. + * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF) have a + * column width of 0. + * - Spacing characters in the East Asian Wide (W) or East Asian Full-width (F) + * category as defined in Unicode Technical Report #11 have a column width of + * 2. + * - East Asian Ambigous characters are taken into account if + * regardCjkAmbiguous flag is enabled. They have a column width of 2. + * - All remaining characters (including all printable ISO 8859-1 and WGL4 + * characters, Unicode control characters, etc.) have a column width of 1. + * + * This implementation assumes that characters are encoded in ISO 10646. + */ + +var wc = {}; + +// Width of a nul character. +wc.nulWidth = 0; + +// Width of a control charater. +wc.controlWidth = 0; + +// Flag whether to consider East Asian Ambiguous characters. +wc.regardCjkAmbiguous = false; + +// Width of an East Asian Ambiguous character. +wc.cjkAmbiguousWidth = 2; + +// Sorted list of non-overlapping intervals of non-spacing characters +// generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" +wc.combining = [ + [ 0x0300, 0x036F ], [ 0x0483, 0x0486 ], [ 0x0488, 0x0489 ], + [ 0x0591, 0x05BD ], [ 0x05BF, 0x05BF ], [ 0x05C1, 0x05C2 ], + [ 0x05C4, 0x05C5 ], [ 0x05C7, 0x05C7 ], [ 0x0600, 0x0603 ], + [ 0x0610, 0x0615 ], [ 0x064B, 0x065E ], [ 0x0670, 0x0670 ], + [ 0x06D6, 0x06E4 ], [ 0x06E7, 0x06E8 ], [ 0x06EA, 0x06ED ], + [ 0x070F, 0x070F ], [ 0x0711, 0x0711 ], [ 0x0730, 0x074A ], + [ 0x07A6, 0x07B0 ], [ 0x07EB, 0x07F3 ], [ 0x0901, 0x0902 ], + [ 0x093C, 0x093C ], [ 0x0941, 0x0948 ], [ 0x094D, 0x094D ], + [ 0x0951, 0x0954 ], [ 0x0962, 0x0963 ], [ 0x0981, 0x0981 ], + [ 0x09BC, 0x09BC ], [ 0x09C1, 0x09C4 ], [ 0x09CD, 0x09CD ], + [ 0x09E2, 0x09E3 ], [ 0x0A01, 0x0A02 ], [ 0x0A3C, 0x0A3C ], + [ 0x0A41, 0x0A42 ], [ 0x0A47, 0x0A48 ], [ 0x0A4B, 0x0A4D ], + [ 0x0A70, 0x0A71 ], [ 0x0A81, 0x0A82 ], [ 0x0ABC, 0x0ABC ], + [ 0x0AC1, 0x0AC5 ], [ 0x0AC7, 0x0AC8 ], [ 0x0ACD, 0x0ACD ], + [ 0x0AE2, 0x0AE3 ], [ 0x0B01, 0x0B01 ], [ 0x0B3C, 0x0B3C ], + [ 0x0B3F, 0x0B3F ], [ 0x0B41, 0x0B43 ], [ 0x0B4D, 0x0B4D ], + [ 0x0B56, 0x0B56 ], [ 0x0B82, 0x0B82 ], [ 0x0BC0, 0x0BC0 ], + [ 0x0BCD, 0x0BCD ], [ 0x0C3E, 0x0C40 ], [ 0x0C46, 0x0C48 ], + [ 0x0C4A, 0x0C4D ], [ 0x0C55, 0x0C56 ], [ 0x0CBC, 0x0CBC ], + [ 0x0CBF, 0x0CBF ], [ 0x0CC6, 0x0CC6 ], [ 0x0CCC, 0x0CCD ], + [ 0x0CE2, 0x0CE3 ], [ 0x0D41, 0x0D43 ], [ 0x0D4D, 0x0D4D ], + [ 0x0DCA, 0x0DCA ], [ 0x0DD2, 0x0DD4 ], [ 0x0DD6, 0x0DD6 ], + [ 0x0E31, 0x0E31 ], [ 0x0E34, 0x0E3A ], [ 0x0E47, 0x0E4E ], + [ 0x0EB1, 0x0EB1 ], [ 0x0EB4, 0x0EB9 ], [ 0x0EBB, 0x0EBC ], + [ 0x0EC8, 0x0ECD ], [ 0x0F18, 0x0F19 ], [ 0x0F35, 0x0F35 ], + [ 0x0F37, 0x0F37 ], [ 0x0F39, 0x0F39 ], [ 0x0F71, 0x0F7E ], + [ 0x0F80, 0x0F84 ], [ 0x0F86, 0x0F87 ], [ 0x0F90, 0x0F97 ], + [ 0x0F99, 0x0FBC ], [ 0x0FC6, 0x0FC6 ], [ 0x102D, 0x1030 ], + [ 0x1032, 0x1032 ], [ 0x1036, 0x1037 ], [ 0x1039, 0x1039 ], + [ 0x1058, 0x1059 ], [ 0x1160, 0x11FF ], [ 0x135F, 0x135F ], + [ 0x1712, 0x1714 ], [ 0x1732, 0x1734 ], [ 0x1752, 0x1753 ], + [ 0x1772, 0x1773 ], [ 0x17B4, 0x17B5 ], [ 0x17B7, 0x17BD ], + [ 0x17C6, 0x17C6 ], [ 0x17C9, 0x17D3 ], [ 0x17DD, 0x17DD ], + [ 0x180B, 0x180D ], [ 0x18A9, 0x18A9 ], [ 0x1920, 0x1922 ], + [ 0x1927, 0x1928 ], [ 0x1932, 0x1932 ], [ 0x1939, 0x193B ], + [ 0x1A17, 0x1A18 ], [ 0x1B00, 0x1B03 ], [ 0x1B34, 0x1B34 ], + [ 0x1B36, 0x1B3A ], [ 0x1B3C, 0x1B3C ], [ 0x1B42, 0x1B42 ], + [ 0x1B6B, 0x1B73 ], [ 0x1DC0, 0x1DCA ], [ 0x1DFE, 0x1DFF ], + [ 0x200B, 0x200F ], [ 0x202A, 0x202E ], [ 0x2060, 0x2063 ], + [ 0x206A, 0x206F ], [ 0x20D0, 0x20EF ], [ 0x302A, 0x302F ], + [ 0x3099, 0x309A ], [ 0xA806, 0xA806 ], [ 0xA80B, 0xA80B ], + [ 0xA825, 0xA826 ], [ 0xFB1E, 0xFB1E ], [ 0xFE00, 0xFE0F ], + [ 0xFE20, 0xFE23 ], [ 0xFEFF, 0xFEFF ], [ 0xFFF9, 0xFFFB ], + [ 0x10A01, 0x10A03 ], [ 0x10A05, 0x10A06 ], [ 0x10A0C, 0x10A0F ], + [ 0x10A38, 0x10A3A ], [ 0x10A3F, 0x10A3F ], [ 0x1D167, 0x1D169 ], + [ 0x1D173, 0x1D182 ], [ 0x1D185, 0x1D18B ], [ 0x1D1AA, 0x1D1AD ], + [ 0x1D242, 0x1D244 ], [ 0xE0001, 0xE0001 ], [ 0xE0020, 0xE007F ], + [ 0xE0100, 0xE01EF ] +]; + +// Sorted list of non-overlapping intervals of East Asian Ambiguous characters +// generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" +wc.ambiguous = [ + [ 0x00A1, 0x00A1 ], [ 0x00A4, 0x00A4 ], [ 0x00A7, 0x00A8 ], + [ 0x00AA, 0x00AA ], [ 0x00AE, 0x00AE ], [ 0x00B0, 0x00B4 ], + [ 0x00B6, 0x00BA ], [ 0x00BC, 0x00BF ], [ 0x00C6, 0x00C6 ], + [ 0x00D0, 0x00D0 ], [ 0x00D7, 0x00D8 ], [ 0x00DE, 0x00E1 ], + [ 0x00E6, 0x00E6 ], [ 0x00E8, 0x00EA ], [ 0x00EC, 0x00ED ], + [ 0x00F0, 0x00F0 ], [ 0x00F2, 0x00F3 ], [ 0x00F7, 0x00FA ], + [ 0x00FC, 0x00FC ], [ 0x00FE, 0x00FE ], [ 0x0101, 0x0101 ], + [ 0x0111, 0x0111 ], [ 0x0113, 0x0113 ], [ 0x011B, 0x011B ], + [ 0x0126, 0x0127 ], [ 0x012B, 0x012B ], [ 0x0131, 0x0133 ], + [ 0x0138, 0x0138 ], [ 0x013F, 0x0142 ], [ 0x0144, 0x0144 ], + [ 0x0148, 0x014B ], [ 0x014D, 0x014D ], [ 0x0152, 0x0153 ], + [ 0x0166, 0x0167 ], [ 0x016B, 0x016B ], [ 0x01CE, 0x01CE ], + [ 0x01D0, 0x01D0 ], [ 0x01D2, 0x01D2 ], [ 0x01D4, 0x01D4 ], + [ 0x01D6, 0x01D6 ], [ 0x01D8, 0x01D8 ], [ 0x01DA, 0x01DA ], + [ 0x01DC, 0x01DC ], [ 0x0251, 0x0251 ], [ 0x0261, 0x0261 ], + [ 0x02C4, 0x02C4 ], [ 0x02C7, 0x02C7 ], [ 0x02C9, 0x02CB ], + [ 0x02CD, 0x02CD ], [ 0x02D0, 0x02D0 ], [ 0x02D8, 0x02DB ], + [ 0x02DD, 0x02DD ], [ 0x02DF, 0x02DF ], [ 0x0391, 0x03A1 ], + [ 0x03A3, 0x03A9 ], [ 0x03B1, 0x03C1 ], [ 0x03C3, 0x03C9 ], + [ 0x0401, 0x0401 ], [ 0x0410, 0x044F ], [ 0x0451, 0x0451 ], + [ 0x2010, 0x2010 ], [ 0x2013, 0x2016 ], [ 0x2018, 0x2019 ], + [ 0x201C, 0x201D ], [ 0x2020, 0x2022 ], [ 0x2024, 0x2027 ], + [ 0x2030, 0x2030 ], [ 0x2032, 0x2033 ], [ 0x2035, 0x2035 ], + [ 0x203B, 0x203B ], [ 0x203E, 0x203E ], [ 0x2074, 0x2074 ], + [ 0x207F, 0x207F ], [ 0x2081, 0x2084 ], [ 0x20AC, 0x20AC ], + [ 0x2103, 0x2103 ], [ 0x2105, 0x2105 ], [ 0x2109, 0x2109 ], + [ 0x2113, 0x2113 ], [ 0x2116, 0x2116 ], [ 0x2121, 0x2122 ], + [ 0x2126, 0x2126 ], [ 0x212B, 0x212B ], [ 0x2153, 0x2154 ], + [ 0x215B, 0x215E ], [ 0x2160, 0x216B ], [ 0x2170, 0x2179 ], + [ 0x2190, 0x2199 ], [ 0x21B8, 0x21B9 ], [ 0x21D2, 0x21D2 ], + [ 0x21D4, 0x21D4 ], [ 0x21E7, 0x21E7 ], [ 0x2200, 0x2200 ], + [ 0x2202, 0x2203 ], [ 0x2207, 0x2208 ], [ 0x220B, 0x220B ], + [ 0x220F, 0x220F ], [ 0x2211, 0x2211 ], [ 0x2215, 0x2215 ], + [ 0x221A, 0x221A ], [ 0x221D, 0x2220 ], [ 0x2223, 0x2223 ], + [ 0x2225, 0x2225 ], [ 0x2227, 0x222C ], [ 0x222E, 0x222E ], + [ 0x2234, 0x2237 ], [ 0x223C, 0x223D ], [ 0x2248, 0x2248 ], + [ 0x224C, 0x224C ], [ 0x2252, 0x2252 ], [ 0x2260, 0x2261 ], + [ 0x2264, 0x2267 ], [ 0x226A, 0x226B ], [ 0x226E, 0x226F ], + [ 0x2282, 0x2283 ], [ 0x2286, 0x2287 ], [ 0x2295, 0x2295 ], + [ 0x2299, 0x2299 ], [ 0x22A5, 0x22A5 ], [ 0x22BF, 0x22BF ], + [ 0x2312, 0x2312 ], [ 0x2460, 0x24E9 ], [ 0x24EB, 0x254B ], + [ 0x2550, 0x2573 ], [ 0x2580, 0x258F ], [ 0x2592, 0x2595 ], + [ 0x25A0, 0x25A1 ], [ 0x25A3, 0x25A9 ], [ 0x25B2, 0x25B3 ], + [ 0x25B6, 0x25B7 ], [ 0x25BC, 0x25BD ], [ 0x25C0, 0x25C1 ], + [ 0x25C6, 0x25C8 ], [ 0x25CB, 0x25CB ], [ 0x25CE, 0x25D1 ], + [ 0x25E2, 0x25E5 ], [ 0x25EF, 0x25EF ], [ 0x2605, 0x2606 ], + [ 0x2609, 0x2609 ], [ 0x260E, 0x260F ], [ 0x2614, 0x2615 ], + [ 0x261C, 0x261C ], [ 0x261E, 0x261E ], [ 0x2640, 0x2640 ], + [ 0x2642, 0x2642 ], [ 0x2660, 0x2661 ], [ 0x2663, 0x2665 ], + [ 0x2667, 0x266A ], [ 0x266C, 0x266D ], [ 0x266F, 0x266F ], + [ 0x273D, 0x273D ], [ 0x2776, 0x277F ], [ 0xE000, 0xF8FF ], + [ 0xFFFD, 0xFFFD ], [ 0xF0000, 0xFFFFD ], [ 0x100000, 0x10FFFD ] +]; + +/** + * Binary search to check if the given unicode character is a space character. + * + * @param {interger} ucs A unicode character code. + * + * @return {boolean} True if the given character is a space character; false + * otherwise. + */ +wc.isSpace = function(ucs) { + // Auxiliary function for binary search in interval table. + var min = 0, max = wc.combining.length - 1; + var mid; + + if (ucs < wc.combining[0][0] || ucs > wc.combining[max][1]) + return false; + while (max >= min) { + mid = Math.floor((min + max) / 2); + if (ucs > wc.combining[mid][1]) { + min = mid + 1; + } else if (ucs < wc.combining[mid][0]) { + max = mid - 1; + } else { + return true; + } + } + + return false; +}; + +/** + * Auxiliary function for checking if the given unicode character is a East + * Asian Ambiguous character. + * + * @param {interger} ucs A unicode character code. + * + * @return {boolean} True if the given character is a East Asian Ambiguous + * character. + */ +wc.isCjkAmbiguous = function(ucs) { + var min = 0, max = wc.ambiguous.length - 1; + var mid; + + if (ucs < wc.ambiguous[0][0] || ucs > wc.ambiguous[max][1]) + return false; + while (max >= min) { + mid = Math.floor((min + max) / 2); + if (ucs > wc.ambiguous[mid][1]) { + min = mid + 1; + } else if (ucs < wc.ambiguous[mid][0]) { + max = mid - 1; + } else { + return true; + } + } + + return false; +}; + +/** + * Determine the column width of the given character. + * + * @param {integer} ucs A unicode character code. + * + * @return {integer} The column width of the given character. + */ +wc.charWidth = function(ucs) { + if (wc.regardCjkAmbiguous) { + return wc.charWidthRegardAmbiguous(ucs); + } else { + return wc.charWidthDisregardAmbiguous(ucs); + } +}; + +/** + * Determine the column width of the given character without considering East + * Asian Ambiguous characters. + * + * @param {integer} ucs A unicode character code. + * + * @return {integer} The column width of the given character. + */ +wc.charWidth = function(ucs) { + // Test for 8-bit control characters. + if (ucs === 0) + return wc.nulWidth; + if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0)) + return wc.controlWidth; + + // Optimize for ASCII characters. + if (ucs < 0x7f) + return 1; + + // Binary search in table of non-spacing characters. + if (wc.isSpace(ucs)) + return 0; + + // If we arrive here, ucs is not a combining or C0/C1 control character. + return 1 + + (ucs >= 0x1100 && + (ucs <= 0x115f || // Hangul Jamo init. consonants + ucs == 0x2329 || ucs == 0x232a || + (ucs >= 0x2e80 && ucs <= 0xa4cf && + ucs != 0x303f) || // CJK ... Yi + (ucs >= 0xac00 && ucs <= 0xd7a3) || // Hangul Syllables + (ucs >= 0xf900 && ucs <= 0xfaff) || // CJK Compatibility Ideographs + (ucs >= 0xfe10 && ucs <= 0xfe19) || // Vertical forms + (ucs >= 0xfe30 && ucs <= 0xfe6f) || // CJK Compatibility Forms + (ucs >= 0xff00 && ucs <= 0xff60) || // Fullwidth Forms + (ucs >= 0xffe0 && ucs <= 0xffe6) || + (ucs >= 0x20000 && ucs <= 0x2fffd) || + (ucs >= 0x30000 && ucs <= 0x3fffd))); +}; + +/** + * Determine the column width of the given character considering East Asian + * Ambiguous characters. + * + * @param {integer} ucs A unicode character code. + * + * @return {integer} The column width of the given character. + */ +wc.charWidthRegardAmbiguous = function(ucs) { + if (wc.isCjkAmbiguous(ucs)) + return wc.cjkAmbiguousWidth; + + return wc.charWidthDisregardAmbiguous(ucs); +}; + +/** + * Determine the column width of the given string. + * + * @param {string} str A string. + * + * @return {integer} The column width of the given string. + */ +wc.strWidth = function(str) { + var width, rv = 0; + + for (var i = 0; i < str.length; i++) { + width = wc.charWidth(str.charCodeAt(i)); + if (width < 0) + return -1; + rv += width; + } + + return rv; +}; + +/** + * Get the substring at the given column offset of the given column width. + * + * @param {string} str The string to get substring from. + * @param {integer} start The starting column offset to get substring. + * @param {integer} opt_width The column width of the substring. + * + * @return {string} The substring. + */ +wc.substr = function(str, start, opt_width) { + var startIndex, endIndex, width; + + for (startIndex = 0, width = 0; startIndex < str.length; startIndex++) { + width += wc.charWidth(str.charCodeAt(startIndex)); + if (width > start) + break; + } + + if (opt_width != undefined) { + for (endIndex = startIndex, width = 0; + endIndex < str.length && width < opt_width; + width += wc.charWidth(str.charCodeAt(endIndex)), endIndex++); + if (width > opt_width) + endIndex--; + return str.substring(startIndex, endIndex); + } + + return str.substr(startIndex); +}; + +/** + * Get substring at the given start and end column offset. + * + * @param {string} str The string to get substring from. + * @param {integer} start The starting column offset. + * @param {integer} end The ending column offset. + * + * @return {string} The substring. + */ +wc.substring = function(str, start, end) { + return wc.substr(str, start, end - start); +}; + +module.exports = wc; + +}); \ No newline at end of file