diff options
Diffstat (limited to 'deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js')
-rw-r--r-- | deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js | 35 |
1 files changed, 18 insertions, 17 deletions
diff --git a/deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js b/deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js index 7a8559824e..1fe3e16011 100644 --- a/deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js +++ b/deps/npm/node_modules/iconv-lite/encodings/dbcs-codec.js @@ -42,7 +42,7 @@ function DBCSCodec(codecOptions, iconv) { this.decodeTables = []; this.decodeTables[0] = UNASSIGNED_NODE.slice(0); // Create root node. - // Sometimes a MBCS char corresponds to a sequence of unicode chars. We store them as arrays of integers here. + // Sometimes a MBCS char corresponds to a sequence of unicode chars. We store them as arrays of integers here. this.decodeTableSeq = []; // Actual mapping tables consist of chunks. Use them to fill up decode tables. @@ -51,7 +51,7 @@ function DBCSCodec(codecOptions, iconv) { this.defaultCharUnicode = iconv.defaultCharUnicode; - + // Encode tables: Unicode -> DBCS. // `encodeTable` is array mapping from unicode char to encoded char. All its values are integers for performance. @@ -60,7 +60,7 @@ function DBCSCodec(codecOptions, iconv) { // == UNASSIGNED -> no conversion found. Output a default char. // <= SEQ_START -> it's an index in encodeTableSeq, see below. The character starts a sequence. this.encodeTable = []; - + // `encodeTableSeq` is used when a sequence of unicode characters is encoded as a single code. We use a tree of // objects where keys correspond to characters in sequence and leafs are the encoded dbcs values. A special DEF_CHAR key // means end of sequence (needed when one sequence is a strict subsequence of another). @@ -78,7 +78,7 @@ function DBCSCodec(codecOptions, iconv) { for (var j = val.from; j <= val.to; j++) skipEncodeChars[j] = true; } - + // Use decode trie to recursively fill out encode tables. this._fillEncodeTable(0, 0, skipEncodeChars); @@ -115,7 +115,7 @@ function DBCSCodec(codecOptions, iconv) { thirdByteNode[i] = NODE_START - fourthByteNodeIdx; for (var i = 0x30; i <= 0x39; i++) fourthByteNode[i] = GB18030_CODE - } + } } DBCSCodec.prototype.encoder = DBCSEncoder; @@ -180,7 +180,7 @@ DBCSCodec.prototype._addDecodeChunk = function(chunk) { else writeTable[curAddr++] = code; // Basic char } - } + } else if (typeof part === "number") { // Integer, meaning increasing sequence starting with prev character. var charCode = writeTable[curAddr - 1] + 1; for (var l = 0; l < part; l++) @@ -211,7 +211,7 @@ DBCSCodec.prototype._setEncodeChar = function(uCode, dbcsCode) { } DBCSCodec.prototype._setEncodeSequence = function(seq, dbcsCode) { - + // Get the root of character tree according to first character of the sequence. var uCode = seq[0]; var bucket = this._getEncodeBucket(uCode); @@ -272,7 +272,7 @@ function DBCSEncoder(options, codec) { // Encoder state this.leadSurrogate = -1; this.seqObj = undefined; - + // Static data this.encodeTable = codec.encodeTable; this.encodeTableSeq = codec.encodeTableSeq; @@ -294,7 +294,7 @@ DBCSEncoder.prototype.write = function(str) { } else { var uCode = nextChar; - nextChar = -1; + nextChar = -1; } // 1. Handle surrogates. @@ -316,7 +316,7 @@ DBCSEncoder.prototype.write = function(str) { // Incomplete surrogate pair - only trail surrogate found. uCode = UNASSIGNED; } - + } } else if (leadSurrogate !== -1) { @@ -357,7 +357,7 @@ DBCSEncoder.prototype.write = function(str) { var subtable = this.encodeTable[uCode >> 8]; if (subtable !== undefined) dbcsCode = subtable[uCode & 0xFF]; - + if (dbcsCode <= SEQ_START) { // Sequence start seqObj = this.encodeTableSeq[SEQ_START-dbcsCode]; continue; @@ -380,7 +380,7 @@ DBCSEncoder.prototype.write = function(str) { // 3. Write dbcsCode character. if (dbcsCode === UNASSIGNED) dbcsCode = this.defaultCharSingleByte; - + if (dbcsCode < 0x100) { newBuf[j++] = dbcsCode; } @@ -427,7 +427,7 @@ DBCSEncoder.prototype.end = function() { newBuf[j++] = this.defaultCharSingleByte; this.leadSurrogate = -1; } - + return newBuf.slice(0, j); } @@ -451,21 +451,21 @@ function DBCSDecoder(options, codec) { DBCSDecoder.prototype.write = function(buf) { var newBuf = Buffer.alloc(buf.length*2), - nodeIdx = this.nodeIdx, + nodeIdx = this.nodeIdx, prevBuf = this.prevBuf, prevBufOffset = this.prevBuf.length, seqStart = -this.prevBuf.length, // idx of the start of current parsed sequence. uCode; if (prevBufOffset > 0) // Make prev buf overlap a little to make it easier to slice later. prevBuf = Buffer.concat([prevBuf, buf.slice(0, 10)]); - + for (var i = 0, j = 0; i < buf.length; i++) { var curByte = (i >= 0) ? buf[i] : prevBuf[i + prevBufOffset]; // Lookup in current trie node. var uCode = this.decodeTables[nodeIdx][curByte]; - if (uCode >= 0) { + if (uCode >= 0) { // Normal character, just use it. } else if (uCode === UNASSIGNED) { // Unknown char. @@ -497,7 +497,7 @@ DBCSDecoder.prototype.write = function(buf) { throw new Error("iconv-lite internal error: invalid decoding table value " + uCode + " at " + nodeIdx + "/" + curByte); // Write the character to buffer, handling higher planes using surrogate pair. - if (uCode > 0xFFFF) { + if (uCode > 0xFFFF) { uCode -= 0x10000; var uCodeLead = 0xD800 + Math.floor(uCode / 0x400); newBuf[j++] = uCodeLead & 0xFF; @@ -552,3 +552,4 @@ function findIdx(table, val) { } return l; } + |