123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321 |
- CodeMirror.defineMode("python", function(conf) {
- var ERRORCLASS = 'error';
-
- function wordRegexp(words) {
- return new RegExp("^((" + words.join(")|(") + "))\\b");
- }
-
- var singleOperators = new RegExp("^[\\+\\-\\*/%&|\\^~<>!]");
- var singleDelimiters = new RegExp('^[\\(\\)\\[\\]\\{\\}@,:`=;\\.]');
- var doubleOperators = new RegExp("^((==)|(!=)|(<=)|(>=)|(<>)|(<<)|(>>)|(//)|(\\*\\*))");
- var doubleDelimiters = new RegExp("^((\\+=)|(\\-=)|(\\*=)|(%=)|(/=)|(&=)|(\\|=)|(\\^=))");
- var tripleDelimiters = new RegExp("^((//=)|(>>=)|(<<=)|(\\*\\*=))");
- var identifiers = new RegExp("^[_A-Za-z][_A-Za-z0-9]*");
- var wordOperators = wordRegexp(['and', 'or', 'not', 'is', 'in']);
- var commonkeywords = ['as', 'assert', 'break', 'class', 'continue',
- 'def', 'del', 'elif', 'else', 'except', 'finally',
- 'for', 'from', 'global', 'if', 'import',
- 'lambda', 'pass', 'raise', 'return',
- 'try', 'while', 'with', 'yield'];
- var commontypes = ['bool', 'classmethod', 'complex', 'dict', 'enumerate',
- 'float', 'frozenset', 'int', 'list', 'object',
- 'property', 'reversed', 'set', 'slice', 'staticmethod',
- 'str', 'super', 'tuple', 'type'];
- var py2 = {'types': ['basestring', 'buffer', 'file', 'long', 'unicode',
- 'xrange'],
- 'keywords': ['exec', 'print']};
- var py3 = {'types': ['bytearray', 'bytes', 'filter', 'map', 'memoryview',
- 'open', 'range', 'zip'],
- 'keywords': ['nonlocal']};
- if (!!conf.mode.version && parseInt(conf.mode.version, 10) === 3) {
- commonkeywords = commonkeywords.concat(py3.keywords);
- commontypes = commontypes.concat(py3.types);
- var stringPrefixes = new RegExp("^(([rb]|(br))?('{3}|\"{3}|['\"]))", "i");
- } else {
- commonkeywords = commonkeywords.concat(py2.keywords);
- commontypes = commontypes.concat(py2.types);
- var stringPrefixes = new RegExp("^(([rub]|(ur)|(br))?('{3}|\"{3}|['\"]))", "i");
- }
- var keywords = wordRegexp(commonkeywords);
- var types = wordRegexp(commontypes);
- var indentInfo = null;
- // tokenizers
- function tokenBase(stream, state) {
- // Handle scope changes
- if (stream.sol()) {
- var scopeOffset = state.scopes[0].offset;
- if (stream.eatSpace()) {
- var lineOffset = stream.indentation();
- if (lineOffset > scopeOffset) {
- indentInfo = 'indent';
- } else if (lineOffset < scopeOffset) {
- indentInfo = 'dedent';
- }
- return null;
- } else {
- if (scopeOffset > 0) {
- dedent(stream, state);
- }
- }
- }
- if (stream.eatSpace()) {
- return null;
- }
-
- var ch = stream.peek();
-
- // Handle Comments
- if (ch === '#') {
- stream.skipToEnd();
- return 'comment';
- }
-
- // Handle Number Literals
- if (stream.match(/^[0-9\.]/, false)) {
- var floatLiteral = false;
- // Floats
- if (stream.match(/^\d*\.\d+(e[\+\-]?\d+)?/i)) { floatLiteral = true; }
- if (stream.match(/^\d+\.\d*/)) { floatLiteral = true; }
- if (stream.match(/^\.\d+/)) { floatLiteral = true; }
- if (floatLiteral) {
- // Float literals may be "imaginary"
- stream.eat(/J/i);
- return 'number';
- }
- // Integers
- var intLiteral = false;
- // Hex
- if (stream.match(/^0x[0-9a-f]+/i)) { intLiteral = true; }
- // Binary
- if (stream.match(/^0b[01]+/i)) { intLiteral = true; }
- // Octal
- if (stream.match(/^0o[0-7]+/i)) { intLiteral = true; }
- // Decimal
- if (stream.match(/^[1-9]\d*(e[\+\-]?\d+)?/)) {
- // Decimal literals may be "imaginary"
- stream.eat(/J/i);
- // TODO - Can you have imaginary longs?
- intLiteral = true;
- }
- // Zero by itself with no other piece of number.
- if (stream.match(/^0(?![\dx])/i)) { intLiteral = true; }
- if (intLiteral) {
- // Integer literals may be "long"
- stream.eat(/L/i);
- return 'number';
- }
- }
-
- // Handle Strings
- if (stream.match(stringPrefixes)) {
- state.tokenize = tokenStringFactory(stream.current());
- return state.tokenize(stream, state);
- }
-
- // Handle operators and Delimiters
- if (stream.match(tripleDelimiters) || stream.match(doubleDelimiters)) {
- return null;
- }
- if (stream.match(doubleOperators)
- || stream.match(singleOperators)
- || stream.match(wordOperators)) {
- return 'operator';
- }
- if (stream.match(singleDelimiters)) {
- return null;
- }
-
- if (stream.match(types)) {
- return 'builtin';
- }
-
- if (stream.match(keywords)) {
- return 'keyword';
- }
-
- if (stream.match(identifiers)) {
- return 'variable';
- }
-
- // Handle non-detected items
- stream.next();
- return ERRORCLASS;
- }
-
- function tokenStringFactory(delimiter) {
- while ('rub'.indexOf(delimiter[0].toLowerCase()) >= 0) {
- delimiter = delimiter.substr(1);
- }
- var delim_re = new RegExp(delimiter);
- var singleline = delimiter.length == 1;
- var OUTCLASS = 'string';
-
- return function tokenString(stream, state) {
- while (!stream.eol()) {
- stream.eatWhile(/[^'"\\]/);
- if (stream.eat('\\')) {
- stream.next();
- if (singleline && stream.eol()) {
- return OUTCLASS;
- }
- } else if (stream.match(delim_re)) {
- state.tokenize = tokenBase;
- return OUTCLASS;
- } else {
- stream.eat(/['"]/);
- }
- }
- if (singleline) {
- if (conf.mode.singleLineStringErrors) {
- OUTCLASS = ERRORCLASS
- } else {
- state.tokenize = tokenBase;
- }
- }
- return OUTCLASS;
- };
- }
-
- function indent(stream, state, type) {
- type = type || 'py';
- var indentUnit = 0;
- if (type === 'py') {
- for (var i = 0; i < state.scopes.length; ++i) {
- if (state.scopes[i].type === 'py') {
- indentUnit = state.scopes[i].offset + conf.indentUnit;
- break;
- }
- }
- } else {
- indentUnit = stream.column() + stream.current().length;
- }
- state.scopes.unshift({
- offset: indentUnit,
- type: type
- });
- }
-
- function dedent(stream, state) {
- if (state.scopes.length == 1) return;
- if (state.scopes[0].type === 'py') {
- var _indent = stream.indentation();
- var _indent_index = -1;
- for (var i = 0; i < state.scopes.length; ++i) {
- if (_indent === state.scopes[i].offset) {
- _indent_index = i;
- break;
- }
- }
- if (_indent_index === -1) {
- return true;
- }
- while (state.scopes[0].offset !== _indent) {
- state.scopes.shift();
- }
- return false
- } else {
- state.scopes.shift();
- return false;
- }
- }
- function tokenLexer(stream, state) {
- indentInfo = null;
- var style = state.tokenize(stream, state);
- var current = stream.current();
- // Handle '.' connected identifiers
- if (current === '.') {
- style = state.tokenize(stream, state);
- current = stream.current();
- if (style === 'variable') {
- return 'variable';
- } else {
- return ERRORCLASS;
- }
- }
-
- // Handle decorators
- if (current === '@') {
- style = state.tokenize(stream, state);
- current = stream.current();
- if (style === 'variable'
- || current === '@staticmethod'
- || current === '@classmethod') {
- return 'meta';
- } else {
- return ERRORCLASS;
- }
- }
-
- // Handle scope changes.
- if (current === 'pass' || current === 'return') {
- state.dedent += 1;
- }
- if ((current === ':' && !state.lambda && state.scopes[0].type == 'py')
- || indentInfo === 'indent') {
- indent(stream, state);
- }
- var delimiter_index = '[({'.indexOf(current);
- if (delimiter_index !== -1) {
- indent(stream, state, '])}'.slice(delimiter_index, delimiter_index+1));
- }
- if (indentInfo === 'dedent') {
- if (dedent(stream, state)) {
- return ERRORCLASS;
- }
- }
- delimiter_index = '])}'.indexOf(current);
- if (delimiter_index !== -1) {
- if (dedent(stream, state)) {
- return ERRORCLASS;
- }
- }
- if (state.dedent > 0 && stream.eol() && state.scopes[0].type == 'py') {
- if (state.scopes.length > 1) state.scopes.shift();
- state.dedent -= 1;
- }
-
- return style;
- }
- var external = {
- startState: function(basecolumn) {
- return {
- tokenize: tokenBase,
- scopes: [{offset:basecolumn || 0, type:'py'}],
- lastToken: null,
- lambda: false,
- dedent: 0
- };
- },
-
- token: function(stream, state) {
- var style = tokenLexer(stream, state);
-
- state.lastToken = {style:style, content: stream.current()};
-
- if (stream.eol() && stream.lambda) {
- state.lambda = false;
- }
-
- return style;
- },
-
- indent: function(state, textAfter) {
- if (state.tokenize != tokenBase) {
- return 0;
- }
-
- return state.scopes[0].offset;
- }
-
- };
- return external;
- });
- CodeMirror.defineMIME("text/x-python", "python");
|