diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 5e58db9..5acd5d8 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -9,7 +9,5 @@ jobs: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - - name: Install claat - run: ./download-claat-linux.sh - name: Build - run: PATH="/tmp/claat:${PATH}" python3 build.py + run: ./build.sh diff --git a/build.sh b/build.sh new file mode 100755 index 0000000..d5bade9 --- /dev/null +++ b/build.sh @@ -0,0 +1,15 @@ +#!/bin/bash + +set -euo pipefail + +./download-claat-linux.sh +PATH="/tmp/claat:${PATH}" python3 ./build.py + +sed -e 's#https://storage.googleapis.com/claat-public#/static#g' -i build/*/index.html + +# The public static hosting seems offline (e.g. https://storage.googleapis.com/claat-public/codelab-elements.css) so we vendor these assets: +# Built by running `USE_BAZEL_VERSION=0.19.1 bazel build :bundle` with patches to: +# 1. `//codelab-elements/google-codelab-analytics`: `suppress = ["strictDependencies", "missingProvide", "checkVars", "missingProperties", "unusedLocalVariables", "unusedLocalVariables"],` +# 2. `//codelab-elements/google-codelab`: `suppress = ["unusedLocalVariables"],` +mkdir build/static +cp static/* build/static/ diff --git a/netlify.toml b/netlify.toml index 4a8d745..964b265 100644 --- a/netlify.toml +++ b/netlify.toml @@ -1,7 +1,7 @@ [build] ignore = "exit 1" #always build on PR even if you can't detect changes in this folder publish = "build" -command = './download-claat-linux.sh && PATH="/tmp/claat:${PATH}" python3 ./build.py' +command = './build.sh' [build.environment] PYTHON_VERSION="3.13" diff --git a/static/LICENSE b/static/LICENSE new file mode 100644 index 0000000..420f8fb --- /dev/null +++ b/static/LICENSE @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2016 Google Inc. All Rights Reserved. + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/static/README.md b/static/README.md new file mode 100644 index 0000000..d8741ec --- /dev/null +++ b/static/README.md @@ -0,0 +1,180 @@ +# Codelab Custom Elements + +The next generation of the codelab elements without any framework or library +dependencies, only the [Custom Elements](https://html.spec.whatwg.org/multipage/custom-elements.html) +standard spec. + +If this is a release bundle, produced with a `bazel build :bundle` command, +you should see `codelab-elements.js`, `codelab-elements.css` and other files, +ready to be added to an HTML page like the following. Only relevant parts are shown: + +```html + + +
+ + ++ * For a fairly comprehensive set of languages see the + * README + * file that came with this source. At a minimum, the lexer should work on a + * number of languages including C and friends, Java, Python, Bash, SQL, HTML, + * XML, CSS, Javascript, and Makefiles. It works passably on Ruby, PHP and Awk + * and a subset of Perl, but, because of commenting conventions, doesn't work on + * Smalltalk, Lisp-like, or CAML-like languages without an explicit lang class. + *
+ * Usage:
} and {@code } tags in your source with
+ * {@code class=prettyprint.}
+ * You can also use the (html deprecated) {@code } tag, but the pretty
+ * printer needs to do more substantial DOM manipulations to support that, so
+ * some css styles may not be preserved.
+ * } or {@code } element to specify the
+ * language, as in {@code }. Any class that
+ * starts with "lang-" followed by a file extension, specifies the file type.
+ * See the "lang-*.js" files in this directory for code that implements
+ * per-language file handlers.
+ *
+ * Change log:
+ * cbeust, 2006/08/22
+ *
+ * Java annotations (start with "@") are now captured as literals ("lit")
+ *
+ * @requires console
+ */
+
+// JSLint declarations
+/*global console, document, navigator, setTimeout, window, define */
+
+/** @define {boolean} */
+var IN_GLOBAL_SCOPE = true;
+
+/**
+ * Split {@code prettyPrint} into multiple timeouts so as not to interfere with
+ * UI events.
+ * If set to {@code false}, {@code prettyPrint()} is synchronous.
+ */
+window['PR_SHOULD_USE_CONTINUATION'] = true;
+
+/**
+ * Pretty print a chunk of code.
+ * @param {string} sourceCodeHtml The HTML to pretty print.
+ * @param {string} opt_langExtension The language name to use.
+ * Typically, a filename extension like 'cpp' or 'java'.
+ * @param {number|boolean} opt_numberLines True to number lines,
+ * or the 1-indexed number of the first line in sourceCodeHtml.
+ * @return {string} code as html, but prettier
+ */
+var prettyPrintOne;
+/**
+ * Find all the {@code } and {@code } tags in the DOM with
+ * {@code class=prettyprint} and prettify them.
+ *
+ * @param {Function} opt_whenDone called when prettifying is done.
+ * @param {HTMLElement|HTMLDocument} opt_root an element or document
+ * containing all the elements to pretty print.
+ * Defaults to {@code document.body}.
+ */
+var prettyPrint;
+
+
+(function () {
+ var win = window;
+ // Keyword lists for various languages.
+ // We use things that coerce to strings to make them compact when minified
+ // and to defeat aggressive optimizers that fold large string constants.
+ var FLOW_CONTROL_KEYWORDS = ["break,continue,do,else,for,if,return,while"];
+ var C_KEYWORDS = [FLOW_CONTROL_KEYWORDS,"auto,case,char,const,default," +
+ "double,enum,extern,float,goto,inline,int,long,register,short,signed," +
+ "sizeof,static,struct,switch,typedef,union,unsigned,void,volatile"];
+ var COMMON_KEYWORDS = [C_KEYWORDS,"catch,class,delete,false,import," +
+ "new,operator,private,protected,public,this,throw,true,try,typeof"];
+ var CPP_KEYWORDS = [COMMON_KEYWORDS,"alignof,align_union,asm,axiom,bool," +
+ "concept,concept_map,const_cast,constexpr,decltype,delegate," +
+ "dynamic_cast,explicit,export,friend,generic,late_check," +
+ "mutable,namespace,nullptr,property,reinterpret_cast,static_assert," +
+ "static_cast,template,typeid,typename,using,virtual,where"];
+ var JAVA_KEYWORDS = [COMMON_KEYWORDS,
+ "abstract,assert,boolean,byte,extends,final,finally,implements,import," +
+ "instanceof,interface,null,native,package,strictfp,super,synchronized," +
+ "throws,transient"];
+ var CSHARP_KEYWORDS = [JAVA_KEYWORDS,
+ "as,base,by,checked,decimal,delegate,descending,dynamic,event," +
+ "fixed,foreach,from,group,implicit,in,internal,into,is,let," +
+ "lock,object,out,override,orderby,params,partial,readonly,ref,sbyte," +
+ "sealed,stackalloc,string,select,uint,ulong,unchecked,unsafe,ushort," +
+ "var,virtual,where"];
+ var COFFEE_KEYWORDS = "all,and,by,catch,class,else,extends,false,finally," +
+ "for,if,in,is,isnt,loop,new,no,not,null,of,off,on,or,return,super,then," +
+ "throw,true,try,unless,until,when,while,yes";
+ var JSCRIPT_KEYWORDS = [COMMON_KEYWORDS,
+ "debugger,eval,export,function,get,null,set,undefined,var,with," +
+ "Infinity,NaN"];
+ var PERL_KEYWORDS = "caller,delete,die,do,dump,elsif,eval,exit,foreach,for," +
+ "goto,if,import,last,local,my,next,no,our,print,package,redo,require," +
+ "sub,undef,unless,until,use,wantarray,while,BEGIN,END";
+ var PYTHON_KEYWORDS = [FLOW_CONTROL_KEYWORDS, "and,as,assert,class,def,del," +
+ "elif,except,exec,finally,from,global,import,in,is,lambda," +
+ "nonlocal,not,or,pass,print,raise,try,with,yield," +
+ "False,True,None"];
+ var RUBY_KEYWORDS = [FLOW_CONTROL_KEYWORDS, "alias,and,begin,case,class," +
+ "def,defined,elsif,end,ensure,false,in,module,next,nil,not,or,redo," +
+ "rescue,retry,self,super,then,true,undef,unless,until,when,yield," +
+ "BEGIN,END"];
+ var RUST_KEYWORDS = [FLOW_CONTROL_KEYWORDS, "as,assert,const,copy,drop," +
+ "enum,extern,fail,false,fn,impl,let,log,loop,match,mod,move,mut,priv," +
+ "pub,pure,ref,self,static,struct,true,trait,type,unsafe,use"];
+ var SH_KEYWORDS = [FLOW_CONTROL_KEYWORDS, "case,done,elif,esac,eval,fi," +
+ "function,in,local,set,then,until"];
+ var ALL_KEYWORDS = [
+ CPP_KEYWORDS, CSHARP_KEYWORDS, JSCRIPT_KEYWORDS, PERL_KEYWORDS,
+ PYTHON_KEYWORDS, RUBY_KEYWORDS, SH_KEYWORDS];
+ var C_TYPES = /^(DIR|FILE|vector|(de|priority_)?queue|list|stack|(const_)?iterator|(multi)?(set|map)|bitset|u?(int|float)\d*)\b/;
+
+ // token style names. correspond to css classes
+ /**
+ * token style for a string literal
+ * @const
+ */
+ var PR_STRING = 'str';
+ /**
+ * token style for a keyword
+ * @const
+ */
+ var PR_KEYWORD = 'kwd';
+ /**
+ * token style for a comment
+ * @const
+ */
+ var PR_COMMENT = 'com';
+ /**
+ * token style for a type
+ * @const
+ */
+ var PR_TYPE = 'typ';
+ /**
+ * token style for a literal value. e.g. 1, null, true.
+ * @const
+ */
+ var PR_LITERAL = 'lit';
+ /**
+ * token style for a punctuation string.
+ * @const
+ */
+ var PR_PUNCTUATION = 'pun';
+ /**
+ * token style for plain text.
+ * @const
+ */
+ var PR_PLAIN = 'pln';
+
+ /**
+ * token style for an sgml tag.
+ * @const
+ */
+ var PR_TAG = 'tag';
+ /**
+ * token style for a markup declaration such as a DOCTYPE.
+ * @const
+ */
+ var PR_DECLARATION = 'dec';
+ /**
+ * token style for embedded source.
+ * @const
+ */
+ var PR_SOURCE = 'src';
+ /**
+ * token style for an sgml attribute name.
+ * @const
+ */
+ var PR_ATTRIB_NAME = 'atn';
+ /**
+ * token style for an sgml attribute value.
+ * @const
+ */
+ var PR_ATTRIB_VALUE = 'atv';
+
+ /**
+ * A class that indicates a section of markup that is not code, e.g. to allow
+ * embedding of line numbers within code listings.
+ * @const
+ */
+ var PR_NOCODE = 'nocode';
+
+
+
+ /**
+ * A set of tokens that can precede a regular expression literal in
+ * javascript
+ * http://web.archive.org/web/20070717142515/http://www.mozilla.org/js/language/js20/rationale/syntax.html
+ * has the full list, but I've removed ones that might be problematic when
+ * seen in languages that don't support regular expression literals.
+ *
+ * Specifically, I've removed any keywords that can't precede a regexp
+ * literal in a syntactically legal javascript program, and I've removed the
+ * "in" keyword since it's not a keyword in many languages, and might be used
+ * as a count of inches.
+ *
+ *
The link above does not accurately describe EcmaScript rules since
+ * it fails to distinguish between (a=++/b/i) and (a++/b/i) but it works
+ * very well in practice.
+ *
+ * @private
+ * @const
+ */
+ var REGEXP_PRECEDER_PATTERN = '(?:^^\\.?|[+-]|[!=]=?=?|\\#|%=?|&&?=?|\\(|\\*=?|[+\\-]=|->|\\/=?|::?|<=?|>>?>?=?|,|;|\\?|@|\\[|~|{|\\^\\^?=?|\\|\\|?=?|break|case|continue|delete|do|else|finally|instanceof|return|throw|try|typeof)\\s*';
+
+ // CAVEAT: this does not properly handle the case where a regular
+ // expression immediately follows another since a regular expression may
+ // have flags for case-sensitivity and the like. Having regexp tokens
+ // adjacent is not valid in any language I'm aware of, so I'm punting.
+ // TODO: maybe style special characters inside a regexp as punctuation.
+
+ /**
+ * Given a group of {@link RegExp}s, returns a {@code RegExp} that globally
+ * matches the union of the sets of strings matched by the input RegExp.
+ * Since it matches globally, if the input strings have a start-of-input
+ * anchor (/^.../), it is ignored for the purposes of unioning.
+ * @param {Array.} regexs non multiline, non-global regexs.
+ * @return {RegExp} a global regex.
+ */
+ function combinePrefixPatterns(regexs) {
+ var capturedGroupIndex = 0;
+
+ var needToFoldCase = false;
+ var ignoreCase = false;
+ for (var i = 0, n = regexs.length; i < n; ++i) {
+ var regex = regexs[i];
+ if (regex.ignoreCase) {
+ ignoreCase = true;
+ } else if (/[a-z]/i.test(regex.source.replace(
+ /\\u[0-9a-f]{4}|\\x[0-9a-f]{2}|\\[^ux]/gi, ''))) {
+ needToFoldCase = true;
+ ignoreCase = false;
+ break;
+ }
+ }
+
+ var escapeCharToCodeUnit = {
+ 'b': 8,
+ 't': 9,
+ 'n': 0xa,
+ 'v': 0xb,
+ 'f': 0xc,
+ 'r': 0xd
+ };
+
+ function decodeEscape(charsetPart) {
+ var cc0 = charsetPart.charCodeAt(0);
+ if (cc0 !== 92 /* \\ */) {
+ return cc0;
+ }
+ var c1 = charsetPart.charAt(1);
+ cc0 = escapeCharToCodeUnit[c1];
+ if (cc0) {
+ return cc0;
+ } else if ('0' <= c1 && c1 <= '7') {
+ return parseInt(charsetPart.substring(1), 8);
+ } else if (c1 === 'u' || c1 === 'x') {
+ return parseInt(charsetPart.substring(2), 16);
+ } else {
+ return charsetPart.charCodeAt(1);
+ }
+ }
+
+ function encodeEscape(charCode) {
+ if (charCode < 0x20) {
+ return (charCode < 0x10 ? '\\x0' : '\\x') + charCode.toString(16);
+ }
+ var ch = String.fromCharCode(charCode);
+ return (ch === '\\' || ch === '-' || ch === ']' || ch === '^')
+ ? "\\" + ch : ch;
+ }
+
+ function caseFoldCharset(charSet) {
+ var charsetParts = charSet.substring(1, charSet.length - 1).match(
+ new RegExp(
+ '\\\\u[0-9A-Fa-f]{4}'
+ + '|\\\\x[0-9A-Fa-f]{2}'
+ + '|\\\\[0-3][0-7]{0,2}'
+ + '|\\\\[0-7]{1,2}'
+ + '|\\\\[\\s\\S]'
+ + '|-'
+ + '|[^-\\\\]',
+ 'g'));
+ var ranges = [];
+ var inverse = charsetParts[0] === '^';
+
+ var out = ['['];
+ if (inverse) { out.push('^'); }
+
+ for (var i = inverse ? 1 : 0, n = charsetParts.length; i < n; ++i) {
+ var p = charsetParts[i];
+ if (/\\[bdsw]/i.test(p)) { // Don't muck with named groups.
+ out.push(p);
+ } else {
+ var start = decodeEscape(p);
+ var end;
+ if (i + 2 < n && '-' === charsetParts[i + 1]) {
+ end = decodeEscape(charsetParts[i + 2]);
+ i += 2;
+ } else {
+ end = start;
+ }
+ ranges.push([start, end]);
+ // If the range might intersect letters, then expand it.
+ // This case handling is too simplistic.
+ // It does not deal with non-latin case folding.
+ // It works for latin source code identifiers though.
+ if (!(end < 65 || start > 122)) {
+ if (!(end < 65 || start > 90)) {
+ ranges.push([Math.max(65, start) | 32, Math.min(end, 90) | 32]);
+ }
+ if (!(end < 97 || start > 122)) {
+ ranges.push([Math.max(97, start) & ~32, Math.min(end, 122) & ~32]);
+ }
+ }
+ }
+ }
+
+ // [[1, 10], [3, 4], [8, 12], [14, 14], [16, 16], [17, 17]]
+ // -> [[1, 12], [14, 14], [16, 17]]
+ ranges.sort(function (a, b) { return (a[0] - b[0]) || (b[1] - a[1]); });
+ var consolidatedRanges = [];
+ var lastRange = [];
+ for (var i = 0; i < ranges.length; ++i) {
+ var range = ranges[i];
+ if (range[0] <= lastRange[1] + 1) {
+ lastRange[1] = Math.max(lastRange[1], range[1]);
+ } else {
+ consolidatedRanges.push(lastRange = range);
+ }
+ }
+
+ for (var i = 0; i < consolidatedRanges.length; ++i) {
+ var range = consolidatedRanges[i];
+ out.push(encodeEscape(range[0]));
+ if (range[1] > range[0]) {
+ if (range[1] + 1 > range[0]) { out.push('-'); }
+ out.push(encodeEscape(range[1]));
+ }
+ }
+ out.push(']');
+ return out.join('');
+ }
+
+ function allowAnywhereFoldCaseAndRenumberGroups(regex) {
+ // Split into character sets, escape sequences, punctuation strings
+ // like ('(', '(?:', ')', '^'), and runs of characters that do not
+ // include any of the above.
+ var parts = regex.source.match(
+ new RegExp(
+ '(?:'
+ + '\\[(?:[^\\x5C\\x5D]|\\\\[\\s\\S])*\\]' // a character set
+ + '|\\\\u[A-Fa-f0-9]{4}' // a unicode escape
+ + '|\\\\x[A-Fa-f0-9]{2}' // a hex escape
+ + '|\\\\[0-9]+' // a back-reference or octal escape
+ + '|\\\\[^ux0-9]' // other escape sequence
+ + '|\\(\\?[:!=]' // start of a non-capturing group
+ + '|[\\(\\)\\^]' // start/end of a group, or line start
+ + '|[^\\x5B\\x5C\\(\\)\\^]+' // run of other characters
+ + ')',
+ 'g'));
+ var n = parts.length;
+
+ // Maps captured group numbers to the number they will occupy in
+ // the output or to -1 if that has not been determined, or to
+ // undefined if they need not be capturing in the output.
+ var capturedGroups = [];
+
+ // Walk over and identify back references to build the capturedGroups
+ // mapping.
+ for (var i = 0, groupIndex = 0; i < n; ++i) {
+ var p = parts[i];
+ if (p === '(') {
+ // groups are 1-indexed, so max group index is count of '('
+ ++groupIndex;
+ } else if ('\\' === p.charAt(0)) {
+ var decimalValue = +p.substring(1);
+ if (decimalValue) {
+ if (decimalValue <= groupIndex) {
+ capturedGroups[decimalValue] = -1;
+ } else {
+ // Replace with an unambiguous escape sequence so that
+ // an octal escape sequence does not turn into a backreference
+ // to a capturing group from an earlier regex.
+ parts[i] = encodeEscape(decimalValue);
+ }
+ }
+ }
+ }
+
+ // Renumber groups and reduce capturing groups to non-capturing groups
+ // where possible.
+ for (var i = 1; i < capturedGroups.length; ++i) {
+ if (-1 === capturedGroups[i]) {
+ capturedGroups[i] = ++capturedGroupIndex;
+ }
+ }
+ for (var i = 0, groupIndex = 0; i < n; ++i) {
+ var p = parts[i];
+ if (p === '(') {
+ ++groupIndex;
+ if (!capturedGroups[groupIndex]) {
+ parts[i] = '(?:';
+ }
+ } else if ('\\' === p.charAt(0)) {
+ var decimalValue = +p.substring(1);
+ if (decimalValue && decimalValue <= groupIndex) {
+ parts[i] = '\\' + capturedGroups[decimalValue];
+ }
+ }
+ }
+
+ // Remove any prefix anchors so that the output will match anywhere.
+ // ^^ really does mean an anchored match though.
+ for (var i = 0; i < n; ++i) {
+ if ('^' === parts[i] && '^' !== parts[i + 1]) { parts[i] = ''; }
+ }
+
+ // Expand letters to groups to handle mixing of case-sensitive and
+ // case-insensitive patterns if necessary.
+ if (regex.ignoreCase && needToFoldCase) {
+ for (var i = 0; i < n; ++i) {
+ var p = parts[i];
+ var ch0 = p.charAt(0);
+ if (p.length >= 2 && ch0 === '[') {
+ parts[i] = caseFoldCharset(p);
+ } else if (ch0 !== '\\') {
+ // TODO: handle letters in numeric escapes.
+ parts[i] = p.replace(
+ /[a-zA-Z]/g,
+ function (ch) {
+ var cc = ch.charCodeAt(0);
+ return '[' + String.fromCharCode(cc & ~32, cc | 32) + ']';
+ });
+ }
+ }
+ }
+
+ return parts.join('');
+ }
+
+ var rewritten = [];
+ for (var i = 0, n = regexs.length; i < n; ++i) {
+ var regex = regexs[i];
+ if (regex.global || regex.multiline) { throw new Error('' + regex); }
+ rewritten.push(
+ '(?:' + allowAnywhereFoldCaseAndRenumberGroups(regex) + ')');
+ }
+
+ return new RegExp(rewritten.join('|'), ignoreCase ? 'gi' : 'g');
+ }
+
+ /**
+ * Split markup into a string of source code and an array mapping ranges in
+ * that string to the text nodes in which they appear.
+ *
+ *
+ * The HTML DOM structure:
+ *
+ * (Element "p"
+ * (Element "b"
+ * (Text "print ")) ; #1
+ * (Text "'Hello '") ; #2
+ * (Element "br") ; #3
+ * (Text " + 'World';")) ; #4
+ *
+ *
+ * corresponds to the HTML
+ * {@code
print 'Hello '
+ 'World';
}.
+ *
+ *
+ * It will produce the output:
+ *
+ * {
+ * sourceCode: "print 'Hello '\n + 'World';",
+ * // 1 2
+ * // 012345678901234 5678901234567
+ * spans: [0, #1, 6, #2, 14, #3, 15, #4]
+ * }
+ *
+ *
+ * where #1 is a reference to the {@code "print "} text node above, and so
+ * on for the other text nodes.
+ *
+ *
+ *
+ * The {@code} spans array is an array of pairs. Even elements are the start
+ * indices of substrings, and odd elements are the text nodes (or BR elements)
+ * that contain the text for those substrings.
+ * Substrings continue until the next index or the end of the source.
+ *
+ *
+ * @param {Node} node an HTML DOM subtree containing source-code.
+ * @param {boolean} isPreformatted true if white-space in text nodes should
+ * be considered significant.
+ * @return {Object} source code and the text nodes in which they occur.
+ */
+ function extractSourceSpans(node, isPreformatted) {
+ var nocode = /(?:^|\s)nocode(?:\s|$)/;
+
+ var chunks = [];
+ var length = 0;
+ var spans = [];
+ var k = 0;
+
+ function walk(node) {
+ var type = node.nodeType;
+ if (type == 1) { // Element
+ if (nocode.test(node.className)) { return; }
+ for (var child = node.firstChild; child; child = child.nextSibling) {
+ walk(child);
+ }
+ var nodeName = node.nodeName.toLowerCase();
+ if ('br' === nodeName || 'li' === nodeName) {
+ chunks[k] = '\n';
+ spans[k << 1] = length++;
+ spans[(k++ << 1) | 1] = node;
+ }
+ } else if (type == 3 || type == 4) { // Text
+ var text = node.nodeValue;
+ if (text.length) {
+ if (!isPreformatted) {
+ text = text.replace(/[ \t\r\n]+/g, ' ');
+ } else {
+ text = text.replace(/\r\n?/g, '\n'); // Normalize newlines.
+ }
+ // TODO: handle tabs here?
+ chunks[k] = text;
+ spans[k << 1] = length;
+ length += text.length;
+ spans[(k++ << 1) | 1] = node;
+ }
+ }
+ }
+
+ walk(node);
+
+ return {
+ sourceCode: chunks.join('').replace(/\n$/, ''),
+ spans: spans
+ };
+ }
+
+ /**
+ * Apply the given language handler to sourceCode and add the resulting
+ * decorations to out.
+ * @param {number} basePos the index of sourceCode within the chunk of source
+ * whose decorations are already present on out.
+ */
+ function appendDecorations(basePos, sourceCode, langHandler, out) {
+ if (!sourceCode) { return; }
+ var job = {
+ sourceCode: sourceCode,
+ basePos: basePos
+ };
+ langHandler(job);
+ out.push.apply(out, job.decorations);
+ }
+
+ var notWs = /\S/;
+
+ /**
+ * Given an element, if it contains only one child element and any text nodes
+ * it contains contain only space characters, return the sole child element.
+ * Otherwise returns undefined.
+ *
+ * This is meant to return the CODE element in {@code
} when
+ * there is a single child element that contains all the non-space textual
+ * content, but not to return anything where there are multiple child elements
+ * as in {@code ......
} or when there
+ * is textual content.
+ */
+ function childContentWrapper(element) {
+ var wrapper = undefined;
+ for (var c = element.firstChild; c; c = c.nextSibling) {
+ var type = c.nodeType;
+ wrapper = (type === 1) // Element Node
+ ? (wrapper ? element : c)
+ : (type === 3) // Text Node
+ ? (notWs.test(c.nodeValue) ? element : wrapper)
+ : wrapper;
+ }
+ return wrapper === element ? undefined : wrapper;
+ }
+
+ /** Given triples of [style, pattern, context] returns a lexing function,
+ * The lexing function interprets the patterns to find token boundaries and
+ * returns a decoration list of the form
+ * [index_0, style_0, index_1, style_1, ..., index_n, style_n]
+ * where index_n is an index into the sourceCode, and style_n is a style
+ * constant like PR_PLAIN. index_n-1 <= index_n, and style_n-1 applies to
+ * all characters in sourceCode[index_n-1:index_n].
+ *
+ * The stylePatterns is a list whose elements have the form
+ * [style : string, pattern : RegExp, DEPRECATED, shortcut : string].
+ *
+ * Style is a style constant like PR_PLAIN, or can be a string of the
+ * form 'lang-FOO', where FOO is a language extension describing the
+ * language of the portion of the token in $1 after pattern executes.
+ * E.g., if style is 'lang-lisp', and group 1 contains the text
+ * '(hello (world))', then that portion of the token will be passed to the
+ * registered lisp handler for formatting.
+ * The text before and after group 1 will be restyled using this decorator
+ * so decorators should take care that this doesn't result in infinite
+ * recursion. For example, the HTML lexer rule for SCRIPT elements looks
+ * something like ['lang-js', /<[s]cript>(.+?)<\/script>/]. This may match
+ * '