123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333 |
- var Buffer = require('buffer').Buffer,
- s = 0,
- S =
- { PARSER_UNINITIALIZED: s++,
- START: s++,
- START_BOUNDARY: s++,
- HEADER_FIELD_START: s++,
- HEADER_FIELD: s++,
- HEADER_VALUE_START: s++,
- HEADER_VALUE: s++,
- HEADER_VALUE_ALMOST_DONE: s++,
- HEADERS_ALMOST_DONE: s++,
- PART_DATA_START: s++,
- PART_DATA: s++,
- PART_END: s++,
- END: s++
- },
-
- f = 1,
- F =
- { PART_BOUNDARY: f,
- LAST_BOUNDARY: f *= 2
- },
-
- LF = 10,
- CR = 13,
- SPACE = 32,
- HYPHEN = 45,
- COLON = 58,
- A = 97,
- Z = 122,
-
- lower = function(c) {
- return c | 0x20;
- };
-
- for (s in S) {
- exports[s] = S[s];
- }
-
- function MultipartParser() {
- this.boundary = null;
- this.boundaryChars = null;
- this.lookbehind = null;
- this.state = S.PARSER_UNINITIALIZED;
-
- this.index = null;
- this.flags = 0;
- }
- exports.MultipartParser = MultipartParser;
-
- MultipartParser.stateToString = function(stateNumber) {
- for (var state in S) {
- var number = S[state];
- if (number === stateNumber) return state;
- }
- };
-
- MultipartParser.prototype.initWithBoundary = function(str) {
- this.boundary = new Buffer(str.length+4);
- this.boundary.write('\r\n--', 0);
- this.boundary.write(str, 4);
- this.lookbehind = new Buffer(this.boundary.length+8);
- this.state = S.START;
-
- this.boundaryChars = {};
- for (var i = 0; i < this.boundary.length; i++) {
- this.boundaryChars[this.boundary[i]] = true;
- }
- };
-
- MultipartParser.prototype.write = function(buffer) {
- var self = this,
- i = 0,
- len = buffer.length,
- prevIndex = this.index,
- index = this.index,
- state = this.state,
- flags = this.flags,
- lookbehind = this.lookbehind,
- boundary = this.boundary,
- boundaryChars = this.boundaryChars,
- boundaryLength = this.boundary.length,
- boundaryEnd = boundaryLength - 1,
- bufferLength = buffer.length,
- c,
- cl,
-
- mark = function(name) {
- self[name+'Mark'] = i;
- },
- clear = function(name) {
- delete self[name+'Mark'];
- },
- callback = function(name, buffer, start, end) {
- if (start !== undefined && start === end) {
- return;
- }
-
- var callbackSymbol = 'on'+name.substr(0, 1).toUpperCase()+name.substr(1);
- if (callbackSymbol in self) {
- self[callbackSymbol](buffer, start, end);
- }
- },
- dataCallback = function(name, clear) {
- var markSymbol = name+'Mark';
- if (!(markSymbol in self)) {
- return;
- }
-
- if (!clear) {
- callback(name, buffer, self[markSymbol], buffer.length);
- self[markSymbol] = 0;
- } else {
- callback(name, buffer, self[markSymbol], i);
- delete self[markSymbol];
- }
- };
-
- for (i = 0; i < len; i++) {
- c = buffer[i];
- switch (state) {
- case S.PARSER_UNINITIALIZED:
- return i;
- case S.START:
- index = 0;
- state = S.START_BOUNDARY;
- case S.START_BOUNDARY:
- if (index == boundary.length - 2) {
- if (c == HYPHEN) {
- flags |= F.LAST_BOUNDARY;
- } else if (c != CR) {
- return i;
- }
- index++;
- break;
- } else if (index - 1 == boundary.length - 2) {
- if (flags & F.LAST_BOUNDARY && c == HYPHEN){
- callback('end');
- state = S.END;
- flags = 0;
- } else if (!(flags & F.LAST_BOUNDARY) && c == LF) {
- index = 0;
- callback('partBegin');
- state = S.HEADER_FIELD_START;
- } else {
- return i;
- }
- break;
- }
-
- if (c != boundary[index+2]) {
- index = -2;
- }
- if (c == boundary[index+2]) {
- index++;
- }
- break;
- case S.HEADER_FIELD_START:
- state = S.HEADER_FIELD;
- mark('headerField');
- index = 0;
- case S.HEADER_FIELD:
- if (c == CR) {
- clear('headerField');
- state = S.HEADERS_ALMOST_DONE;
- break;
- }
-
- index++;
- if (c == HYPHEN) {
- break;
- }
-
- if (c == COLON) {
- if (index == 1) {
- // empty header field
- return i;
- }
- dataCallback('headerField', true);
- state = S.HEADER_VALUE_START;
- break;
- }
-
- cl = lower(c);
- if (cl < A || cl > Z) {
- return i;
- }
- break;
- case S.HEADER_VALUE_START:
- if (c == SPACE) {
- break;
- }
-
- mark('headerValue');
- state = S.HEADER_VALUE;
- case S.HEADER_VALUE:
- if (c == CR) {
- dataCallback('headerValue', true);
- callback('headerEnd');
- state = S.HEADER_VALUE_ALMOST_DONE;
- }
- break;
- case S.HEADER_VALUE_ALMOST_DONE:
- if (c != LF) {
- return i;
- }
- state = S.HEADER_FIELD_START;
- break;
- case S.HEADERS_ALMOST_DONE:
- if (c != LF) {
- return i;
- }
-
- callback('headersEnd');
- state = S.PART_DATA_START;
- break;
- case S.PART_DATA_START:
- state = S.PART_DATA;
- mark('partData');
- case S.PART_DATA:
- prevIndex = index;
-
- if (index === 0) {
- // boyer-moore derrived algorithm to safely skip non-boundary data
- i += boundaryEnd;
- while (i < bufferLength && !(buffer[i] in boundaryChars)) {
- i += boundaryLength;
- }
- i -= boundaryEnd;
- c = buffer[i];
- }
-
- if (index < boundary.length) {
- if (boundary[index] == c) {
- if (index === 0) {
- dataCallback('partData', true);
- }
- index++;
- } else {
- index = 0;
- }
- } else if (index == boundary.length) {
- index++;
- if (c == CR) {
- // CR = part boundary
- flags |= F.PART_BOUNDARY;
- } else if (c == HYPHEN) {
- // HYPHEN = end boundary
- flags |= F.LAST_BOUNDARY;
- } else {
- index = 0;
- }
- } else if (index - 1 == boundary.length) {
- if (flags & F.PART_BOUNDARY) {
- index = 0;
- if (c == LF) {
- // unset the PART_BOUNDARY flag
- flags &= ~F.PART_BOUNDARY;
- callback('partEnd');
- callback('partBegin');
- state = S.HEADER_FIELD_START;
- break;
- }
- } else if (flags & F.LAST_BOUNDARY) {
- if (c == HYPHEN) {
- callback('partEnd');
- callback('end');
- state = S.END;
- flags = 0;
- } else {
- index = 0;
- }
- } else {
- index = 0;
- }
- }
-
- if (index > 0) {
- // when matching a possible boundary, keep a lookbehind reference
- // in case it turns out to be a false lead
- lookbehind[index-1] = c;
- } else if (prevIndex > 0) {
- // if our boundary turned out to be rubbish, the captured lookbehind
- // belongs to partData
- callback('partData', lookbehind, 0, prevIndex);
- prevIndex = 0;
- mark('partData');
-
- // reconsider the current character even so it interrupted the sequence
- // it could be the beginning of a new sequence
- i--;
- }
-
- break;
- case S.END:
- break;
- default:
- return i;
- }
- }
-
- dataCallback('headerField');
- dataCallback('headerValue');
- dataCallback('partData');
-
- this.index = index;
- this.state = state;
- this.flags = flags;
-
- return len;
- };
-
- MultipartParser.prototype.end = function() {
- var callback = function(self, name) {
- var callbackSymbol = 'on'+name.substr(0, 1).toUpperCase()+name.substr(1);
- if (callbackSymbol in self) {
- self[callbackSymbol]();
- }
- };
- if ((this.state == S.HEADER_FIELD_START && this.index === 0) ||
- (this.state == S.PART_DATA && this.index == this.boundary.length)) {
- callback(this, 'partEnd');
- callback(this, 'end');
- } else if (this.state != S.END) {
- return new Error('MultipartParser.end(): stream ended unexpectedly: ' + this.explain());
- }
- };
-
- MultipartParser.prototype.explain = function() {
- return 'state = ' + MultipartParser.stateToString(this.state);
- };
|