1
0
Fork 0
mirror of https://github.com/mozilla/pdf.js.git synced 2025-04-25 09:38:06 +02:00

CMaps binary packing

This commit is contained in:
Yury Delendik 2014-03-14 13:22:02 -05:00
parent e5cd75083f
commit 69efd9cb96
13 changed files with 1156 additions and 35 deletions

View file

@ -15,7 +15,7 @@
* limitations under the License.
*/
/* globals Util, isString, isInt, warn, error, isCmd, isEOF, isName, Lexer,
isStream, StringStream */
isStream, StringStream, PDFJS, assert */
'use strict';
@ -275,6 +275,314 @@ var IdentityCMap = (function IdentityCMapClosure() {
return IdentityCMap;
})();
var BinaryCMapReader = (function BinaryCMapReaderClosure() {
function fetchBinaryData(url) {
var nonBinaryRequest = PDFJS.disableWorker;
var request = new XMLHttpRequest();
request.open('GET', url, false);
if (!nonBinaryRequest) {
try {
request.responseType = 'arraybuffer';
nonBinaryRequest = request.responseType !== 'arraybuffer';
} catch (e) {
nonBinaryRequest = true;
}
}
if (nonBinaryRequest && request.overrideMimeType) {
request.overrideMimeType('text/plain; charset=x-user-defined');
}
request.send(null);
if (request.status === 0 && /^https?:/i.test(url)) {
error('Unable to get binary cMap at: ' + url);
}
if (nonBinaryRequest) {
var data = Array.prototype.map.call(request.responseText, function (ch) {
return ch.charCodeAt(0) & 255;
});
return new Uint8Array(data);
}
return new Uint8Array(request.response);
}
function hexToInt(a, size) {
var n = 0;
for (var i = 0; i <= size; i++) {
n = (n << 8) | a[i];
}
return n >>> 0;
}
function hexToStr(a, size) {
return String.fromCharCode.apply(null, a.subarray(0, size + 1));
}
function addHex(a, b, size) {
var c = 0;
for (var i = size; i >= 0; i--) {
c += a[i] + b[i];
a[i] = c & 255;
c >>= 8;
}
}
function incHex(a, size) {
var c = 1;
for (var i = size; i >= 0 && c > 0; i--) {
c += a[i];
a[i] = c & 255;
c >>= 8;
}
}
var MAX_NUM_SIZE = 16;
var MAX_ENCODED_NUM_SIZE = 19; // ceil(MAX_NUM_SIZE * 7 / 8)
function BinaryCMapStream(data) {
this.buffer = data;
this.pos = 0;
this.end = data.length;
this.tmpBuf = new Uint8Array(MAX_ENCODED_NUM_SIZE);
}
BinaryCMapStream.prototype = {
readByte: function () {
if (this.pos >= this.end) {
return -1;
}
return this.buffer[this.pos++];
},
readNumber: function () {
var n = 0;
var last;
do {
var b = this.readByte();
if (b < 0) {
error('unexpected EOF in bcmap');
}
last = !(b & 0x80);
n = (n << 7) | (b & 0x7F);
} while (!last);
return n;
},
readSigned: function () {
var n = this.readNumber();
return (n & 1) ? ~(n >>> 1) : n >>> 1;
},
readHex: function (num, size) {
num.set(this.buffer.subarray(this.pos,
this.pos + size + 1));
this.pos += size + 1;
},
readHexNumber: function (num, size) {
var last;
var stack = this.tmpBuf, sp = 0;
do {
var b = this.readByte();
if (b < 0) {
error('unexpected EOF in bcmap');
}
last = !(b & 0x80);
stack[sp++] = b & 0x7F;
} while (!last);
var i = size, buffer = 0, bufferSize = 0;
while (i >= 0) {
while (bufferSize < 8 && stack.length > 0) {
buffer = (stack[--sp] << bufferSize) | buffer;
bufferSize += 7;
}
num[i] = buffer & 255;
i--;
buffer >>= 8;
bufferSize -= 8;
}
},
readHexSigned: function (num, size) {
this.readHexNumber(num, size);
var sign = num[size] & 1 ? 255 : 0;
var c = 0;
for (var i = 0; i <= size; i++) {
c = ((c & 1) << 8) | num[i];
num[i] = (c >> 1) ^ sign;
}
},
readString: function () {
var len = this.readNumber();
var s = '';
for (var i = 0; i < len; i++) {
s += String.fromCharCode(this.readNumber());
}
return s;
}
};
function processBinaryCMap(url, cMap, extend) {
var data = fetchBinaryData(url);
var stream = new BinaryCMapStream(data);
var header = stream.readByte();
cMap.vertical = !!(header & 1);
var useCMap = null;
var start = new Uint8Array(MAX_NUM_SIZE);
var end = new Uint8Array(MAX_NUM_SIZE);
var char = new Uint8Array(MAX_NUM_SIZE);
var charCode = new Uint8Array(MAX_NUM_SIZE);
var tmp = new Uint8Array(MAX_NUM_SIZE);
var code;
var b;
while ((b = stream.readByte()) >= 0) {
var type = b >> 5;
if (type === 7) { // metadata, e.g. comment or usecmap
switch (b & 0x1F) {
case 0:
stream.readString(); // skipping comment
break;
case 1:
useCMap = stream.readString();
break;
}
continue;
}
var sequence = !!(b & 0x10);
var dataSize = b & 15;
assert(dataSize + 1 <= MAX_NUM_SIZE);
var ucs2DataSize = 1;
var subitemsCount = stream.readNumber();
switch (type) {
case 0: // codespacerange
stream.readHex(start, dataSize);
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
cMap.addCodespaceRange(dataSize + 1, hexToInt(start, dataSize),
hexToInt(end, dataSize));
for (var i = 1; i < subitemsCount; i++) {
incHex(end, dataSize);
stream.readHexNumber(start, dataSize);
addHex(start, end, dataSize);
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
cMap.addCodespaceRange(dataSize + 1, hexToInt(start, dataSize),
hexToInt(end, dataSize));
}
break;
case 1: // notdefrange
stream.readHex(start, dataSize);
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
code = stream.readNumber();
// undefined range, skipping
for (var i = 1; i < subitemsCount; i++) {
incHex(end, dataSize);
stream.readHexNumber(start, dataSize);
addHex(start, end, dataSize);
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
code = stream.readNumber();
// nop
}
break;
case 2: // cidchar
stream.readHex(char, dataSize);
code = stream.readNumber();
cMap.mapOne(hexToInt(char, dataSize), String.fromCharCode(code));
for (var i = 1; i < subitemsCount; i++) {
incHex(char, dataSize);
if (!sequence) {
stream.readHexNumber(tmp, dataSize);
addHex(char, tmp, dataSize);
}
code = stream.readSigned() + (code + 1);
cMap.mapOne(hexToInt(char, dataSize), String.fromCharCode(code));
}
break;
case 3: // cidrange
stream.readHex(start, dataSize);
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
code = stream.readNumber();
cMap.mapRange(hexToInt(start, dataSize), hexToInt(end, dataSize),
String.fromCharCode(code));
for (var i = 1; i < subitemsCount; i++) {
incHex(end, dataSize);
if (!sequence) {
stream.readHexNumber(start, dataSize);
addHex(start, end, dataSize);
} else {
start.set(end);
}
stream.readHexNumber(end, dataSize);
addHex(end, start, dataSize);
code = stream.readNumber();
cMap.mapRange(hexToInt(start, dataSize), hexToInt(end, dataSize),
String.fromCharCode(code));
}
break;
case 4: // bfchar
stream.readHex(char, ucs2DataSize);
stream.readHex(charCode, dataSize);
cMap.mapOne(hexToInt(char, ucs2DataSize),
hexToStr(charCode, dataSize));
for (var i = 1; i < subitemsCount; i++) {
incHex(char, ucs2DataSize);
if (!sequence) {
stream.readHexNumber(tmp, ucs2DataSize);
addHex(char, tmp, ucs2DataSize);
}
incHex(charCode, dataSize);
stream.readHexSigned(tmp, dataSize);
addHex(charCode, tmp, dataSize);
cMap.mapOne(hexToInt(char, ucs2DataSize),
hexToStr(charCode, dataSize));
}
break;
case 5: // bfrange
stream.readHex(start, ucs2DataSize);
stream.readHexNumber(end, ucs2DataSize);
addHex(end, start, ucs2DataSize);
stream.readHex(charCode, dataSize);
cMap.mapRange(hexToInt(start, ucs2DataSize),
hexToInt(end, ucs2DataSize),
hexToStr(charCode, dataSize));
for (var i = 1; i < subitemsCount; i++) {
incHex(end, ucs2DataSize);
if (!sequence) {
stream.readHexNumber(start, ucs2DataSize);
addHex(start, end, ucs2DataSize);
} else {
start.set(end);
}
stream.readHexNumber(end, ucs2DataSize);
addHex(end, start, ucs2DataSize);
stream.readHex(charCode, dataSize);
cMap.mapRange(hexToInt(start, ucs2DataSize),
hexToInt(end, ucs2DataSize),
hexToStr(charCode, dataSize));
}
break;
default:
error('Unknown type: ' + type);
break;
}
}
if (useCMap) {
extend(useCMap);
}
return cMap;
}
function BinaryCMapReader() {}
BinaryCMapReader.prototype = {
read: processBinaryCMap
};
return BinaryCMapReader;
})();
var CMapFactory = (function CMapFactoryClosure() {
function strToInt(str) {
var a = 0;
@ -417,7 +725,7 @@ var CMapFactory = (function CMapFactoryClosure() {
}
}
function parseCMap(cMap, lexer, builtInCMapUrl, useCMap) {
function parseCMap(cMap, lexer, builtInCMapParams, useCMap) {
var previous;
var embededUseCMap;
objLoop: while (true) {
@ -463,28 +771,41 @@ var CMapFactory = (function CMapFactoryClosure() {
useCMap = embededUseCMap;
}
if (useCMap) {
cMap.useCMap = createBuiltInCMap(useCMap, builtInCMapUrl);
// If there aren't any code space ranges defined clone all the parent ones
// into this cMap.
if (cMap.numCodespaceRanges === 0) {
var useCodespaceRanges = cMap.useCMap.codespaceRanges;
for (var i = 0; i < useCodespaceRanges.length; i++) {
cMap.codespaceRanges[i] = useCodespaceRanges[i].slice();
}
cMap.numCodespaceRanges = cMap.useCMap.numCodespaceRanges;
}
// Merge the map into the current one, making sure not to override
// any previously defined entries.
for (var key in cMap.useCMap.map) {
if (key in cMap.map) {
continue;
}
cMap.map[key] = cMap.useCMap.map[key];
}
extendCMap(cMap, builtInCMapParams, useCMap);
}
}
function createBuiltInCMap(name, builtInCMapUrl) {
function extendCMap(cMap, builtInCMapParams, useCMap) {
cMap.useCMap = createBuiltInCMap(useCMap, builtInCMapParams);
// If there aren't any code space ranges defined clone all the parent ones
// into this cMap.
if (cMap.numCodespaceRanges === 0) {
var useCodespaceRanges = cMap.useCMap.codespaceRanges;
for (var i = 0; i < useCodespaceRanges.length; i++) {
cMap.codespaceRanges[i] = useCodespaceRanges[i].slice();
}
cMap.numCodespaceRanges = cMap.useCMap.numCodespaceRanges;
}
// Merge the map into the current one, making sure not to override
// any previously defined entries.
for (var key in cMap.useCMap.map) {
if (key in cMap.map) {
continue;
}
cMap.map[key] = cMap.useCMap.map[key];
}
}
function parseBinaryCMap(name, builtInCMapParams) {
var url = builtInCMapParams.url + name + '.bcmap';
var cMap = new CMap(true);
new BinaryCMapReader().read(url, cMap, function (useCMap) {
extendCMap(cMap, builtInCMapParams, useCMap);
});
return cMap;
}
function createBuiltInCMap(name, builtInCMapParams) {
if (name === 'Identity-H') {
return new IdentityCMap(false, 2);
} else if (name === 'Identity-V') {
@ -493,9 +814,14 @@ var CMapFactory = (function CMapFactoryClosure() {
if (BUILT_IN_CMAPS.indexOf(name) === -1) {
error('Unknown cMap name: ' + name);
}
assert (builtInCMapParams, 'buildin cmap parameters are not provided');
if (builtInCMapParams.packed) {
return parseBinaryCMap(name, builtInCMapParams);
}
var request = new XMLHttpRequest();
var url = builtInCMapUrl + name;
var url = builtInCMapParams.url + name;
request.open('GET', url, false);
request.send(null);
if (request.status === 0 && /^https?:/i.test(url)) {
@ -503,19 +829,19 @@ var CMapFactory = (function CMapFactoryClosure() {
}
var cMap = new CMap(true);
var lexer = new Lexer(new StringStream(request.responseText));
parseCMap(cMap, lexer, builtInCMapUrl, null);
parseCMap(cMap, lexer, builtInCMapParams, null);
return cMap;
}
return {
create: function (encoding, builtInCMapUrl, useCMap) {
create: function (encoding, builtInCMapParams, useCMap) {
if (isName(encoding)) {
return createBuiltInCMap(encoding.name, builtInCMapUrl);
return createBuiltInCMap(encoding.name, builtInCMapParams);
} else if (isStream(encoding)) {
var cMap = new CMap();
var lexer = new Lexer(encoding);
try {
parseCMap(cMap, lexer, builtInCMapUrl, useCMap);
parseCMap(cMap, lexer, builtInCMapParams, useCMap);
} catch (e) {
warn('Invalid CMap data. ' + e);
}