mirror of
https://github.com/mozilla/pdf.js.git
synced 2025-04-26 01:58:06 +02:00
lookChar refactoring
This commit is contained in:
Yury Delendik
parent
ba87d2fe11
commit
19e8f2f059
8 changed files with 251 additions and 272 deletions
288
src/parser.js
288
src/parser.js
|
|
@ -59,8 +59,6 @@ var Parser = (function ParserClosure() {
|
|||
if (isCmd(this.buf2, 'ID')) {
|
||||
this.buf1 = this.buf2;
|
||||
this.buf2 = null;
|
||||
// skip byte after ID
|
||||
this.lexer.skip();
|
||||
} else {
|
||||
this.buf1 = this.buf2;
|
||||
this.buf2 = this.lexer.getObj();
|
||||
|
|
@ -155,9 +153,8 @@ var Parser = (function ParserClosure() {
|
|||
|
||||
// searching for the /EI\s/
|
||||
var state = 0, ch, i, ii;
|
||||
while (state != 4 &&
|
||||
(ch = stream.getByte()) !== null && ch !== undefined) {
|
||||
switch (ch) {
|
||||
while (state != 4 && (ch = stream.getByte()) !== -1) {
|
||||
switch (ch | 0) {
|
||||
case 0x20:
|
||||
case 0x0D:
|
||||
case 0x0A:
|
||||
|
|
@ -165,7 +162,8 @@ var Parser = (function ParserClosure() {
|
|||
var followingBytes = stream.peekBytes(5);
|
||||
for (i = 0, ii = followingBytes.length; i < ii; i++) {
|
||||
ch = followingBytes[i];
|
||||
if (ch !== 0x0A && ch != 0x0D && (ch < 0x20 || ch > 0x7F)) {
|
||||
if (ch !== 0x0A && ch !== 0x0D && (ch < 0x20 || ch > 0x7F)) {
|
||||
// not a LF, CR, SPACE or any visible ASCII character
|
||||
state = 0;
|
||||
break; // some binary stuff found, resetting the state
|
||||
}
|
||||
|
|
@ -206,7 +204,7 @@ var Parser = (function ParserClosure() {
|
|||
|
||||
// get stream start position
|
||||
lexer.skipToNextLine();
|
||||
var pos = stream.pos;
|
||||
var pos = stream.pos - 1;
|
||||
|
||||
// get length
|
||||
var length = this.fetchIfRef(dict.get('Length'));
|
||||
|
|
@ -215,6 +213,8 @@ var Parser = (function ParserClosure() {
|
|||
|
||||
// skip over the stream data
|
||||
stream.pos = pos + length;
|
||||
lexer.nextChar();
|
||||
|
||||
this.shift(); // '>>'
|
||||
this.shift(); // 'stream'
|
||||
if (!isCmd(this.buf1, 'endstream')) {
|
||||
|
|
@ -254,6 +254,8 @@ var Parser = (function ParserClosure() {
|
|||
error('Missing endstream');
|
||||
}
|
||||
length = skipped;
|
||||
|
||||
lexer.nextChar();
|
||||
this.shift();
|
||||
this.shift();
|
||||
}
|
||||
|
|
@ -344,6 +346,8 @@ var Parser = (function ParserClosure() {
|
|||
var Lexer = (function LexerClosure() {
|
||||
function Lexer(stream, knownCommands) {
|
||||
this.stream = stream;
|
||||
this.nextChar();
|
||||
|
||||
// The PDFs might have "glued" commands with other commands, operands or
|
||||
// literals, e.g. "q1". The knownCommands is a dictionary of the valid
|
||||
// commands and their prefixes. The prefixes are built the following way:
|
||||
|
|
@ -355,7 +359,8 @@ var Lexer = (function LexerClosure() {
|
|||
}
|
||||
|
||||
Lexer.isSpace = function Lexer_isSpace(ch) {
|
||||
return ch == ' ' || ch == '\t' || ch == '\x0d' || ch == '\x0a';
|
||||
// space is one of the following characters: SPACE, TAB, CR, or LF
|
||||
return ch === 0x20 || ch === 0x09 || ch === 0x0D || ch === 0x0A;
|
||||
};
|
||||
|
||||
// A '1' in this array means the character is white space. A '1' or
|
||||
|
|
@ -380,36 +385,40 @@ var Lexer = (function LexerClosure() {
|
|||
];
|
||||
|
||||
function toHexDigit(ch) {
|
||||
if (ch >= '0' && ch <= '9')
|
||||
return ch.charCodeAt(0) - 48;
|
||||
ch = ch.toUpperCase();
|
||||
if (ch >= 'A' && ch <= 'F')
|
||||
return ch.charCodeAt(0) - 55;
|
||||
if (ch >= 0x30 && ch <= 0x39) { // '0'-'9'
|
||||
return ch & 0x0F;
|
||||
}
|
||||
if ((ch >= 0x41 && ch <= 0x46) || (ch >= 0x61 && ch <= 0x66)) {
|
||||
// 'A'-'F', 'a'-'f'
|
||||
return (ch & 0x0F) + 9;
|
||||
}
|
||||
return -1;
|
||||
}
|
||||
|
||||
Lexer.prototype = {
|
||||
getNumber: function Lexer_getNumber(ch) {
|
||||
nextChar: function Lexer_nextChar() {
|
||||
return (this.currentChar = this.stream.getByte());
|
||||
},
|
||||
getNumber: function Lexer_getNumber() {
|
||||
var floating = false;
|
||||
var str = ch;
|
||||
var stream = this.stream;
|
||||
while ((ch = stream.lookChar())) {
|
||||
if (ch == '.' && !floating) {
|
||||
str += ch;
|
||||
var ch = this.currentChar;
|
||||
var str = String.fromCharCode(ch);
|
||||
while ((ch = this.nextChar()) >= 0) {
|
||||
if (ch === 0x2E && !floating) { // '.'
|
||||
str += '.';
|
||||
floating = true;
|
||||
} else if (ch == '-') {
|
||||
} else if (ch === 0x2D) { // '-'
|
||||
// ignore minus signs in the middle of numbers to match
|
||||
// Adobe's behavior
|
||||
warn('Badly formated number');
|
||||
} else if (ch >= '0' && ch <= '9') {
|
||||
str += ch;
|
||||
} else if (ch == 'e' || ch == 'E') {
|
||||
} else if (ch >= 0x30 && ch <= 0x39) { // '0'-'9'
|
||||
str += String.fromCharCode(ch);
|
||||
} else if (ch === 0x45 || ch === 0x65) { // 'E', 'e'
|
||||
floating = true;
|
||||
} else {
|
||||
// the last character doesn't belong to us
|
||||
break;
|
||||
}
|
||||
stream.skip();
|
||||
}
|
||||
var value = parseFloat(str);
|
||||
if (isNaN(value))
|
||||
|
|
@ -420,148 +429,150 @@ var Lexer = (function LexerClosure() {
|
|||
var numParen = 1;
|
||||
var done = false;
|
||||
var str = '';
|
||||
var stream = this.stream;
|
||||
var ch;
|
||||
do {
|
||||
ch = stream.getChar();
|
||||
switch (ch) {
|
||||
case null:
|
||||
case undefined:
|
||||
|
||||
var ch = this.nextChar();
|
||||
while (true) {
|
||||
var charBuffered = false;
|
||||
switch (ch | 0) {
|
||||
case -1:
|
||||
warn('Unterminated string');
|
||||
done = true;
|
||||
break;
|
||||
case '(':
|
||||
case 0x28: // '('
|
||||
++numParen;
|
||||
str += ch;
|
||||
str += '(';
|
||||
break;
|
||||
case ')':
|
||||
case 0x29: // ')'
|
||||
if (--numParen === 0) {
|
||||
this.nextChar(); // consume strings ')'
|
||||
done = true;
|
||||
} else {
|
||||
str += ch;
|
||||
str += ')';
|
||||
}
|
||||
break;
|
||||
case '\\':
|
||||
ch = stream.getChar();
|
||||
case 0x5C: // '\\'
|
||||
ch = this.nextChar();
|
||||
switch (ch) {
|
||||
case null:
|
||||
case undefined:
|
||||
case -1:
|
||||
warn('Unterminated string');
|
||||
done = true;
|
||||
break;
|
||||
case 'n':
|
||||
case 0x6E: // 'n'
|
||||
str += '\n';
|
||||
break;
|
||||
case 'r':
|
||||
case 0x72: // 'r'
|
||||
str += '\r';
|
||||
break;
|
||||
case 't':
|
||||
case 0x74: // 't'
|
||||
str += '\t';
|
||||
break;
|
||||
case 'b':
|
||||
case 0x62: // 'b'
|
||||
str += '\b';
|
||||
break;
|
||||
case 'f':
|
||||
case 0x66: // 'f'
|
||||
str += '\f';
|
||||
break;
|
||||
case '\\':
|
||||
case '(':
|
||||
case ')':
|
||||
str += ch;
|
||||
case 0x5C: // '\'
|
||||
case 0x28: // '('
|
||||
case 0x29: // ')'
|
||||
str += String.fromCharCode(ch);
|
||||
break;
|
||||
case '0': case '1': case '2': case '3':
|
||||
case '4': case '5': case '6': case '7':
|
||||
var x = ch - '0';
|
||||
ch = stream.lookChar();
|
||||
if (ch >= '0' && ch <= '7') {
|
||||
stream.skip();
|
||||
x = (x << 3) + (ch - '0');
|
||||
ch = stream.lookChar();
|
||||
if (ch >= '0' && ch <= '7') {
|
||||
stream.skip();
|
||||
x = (x << 3) + (ch - '0');
|
||||
case 0x30: case 0x31: case 0x32: case 0x33: // '0'-'3'
|
||||
case 0x34: case 0x35: case 0x36: case 0x37: // '4'-'7'
|
||||
var x = ch & 0x0F;
|
||||
ch = this.nextChar();
|
||||
charBuffered = true;
|
||||
if (ch >= 0x30 && ch <= 0x37) { // '0'-'7'
|
||||
x = (x << 3) + (ch & 0x0F);
|
||||
ch = this.nextChar();
|
||||
if (ch >= 0x30 && ch <= 0x37) { // '0'-'7'
|
||||
charBuffered = false;
|
||||
x = (x << 3) + (ch & 0x0F);
|
||||
}
|
||||
}
|
||||
|
||||
str += String.fromCharCode(x);
|
||||
break;
|
||||
case '\r':
|
||||
ch = stream.lookChar();
|
||||
if (ch == '\n')
|
||||
stream.skip();
|
||||
break;
|
||||
case '\n':
|
||||
case 0x0A: case 0x0D: // LF, CR
|
||||
break;
|
||||
default:
|
||||
str += ch;
|
||||
str += String.fromCharCode(ch);
|
||||
break;
|
||||
}
|
||||
break;
|
||||
default:
|
||||
str += ch;
|
||||
str += String.fromCharCode(ch);
|
||||
break;
|
||||
}
|
||||
} while (!done);
|
||||
if (done) {
|
||||
break;
|
||||
}
|
||||
if (!charBuffered) {
|
||||
ch = this.nextChar();
|
||||
}
|
||||
}
|
||||
return str;
|
||||
},
|
||||
getName: function Lexer_getName(ch) {
|
||||
var str = '';
|
||||
var stream = this.stream;
|
||||
while (!!(ch = stream.lookChar()) && !specialChars[ch.charCodeAt(0)]) {
|
||||
stream.skip();
|
||||
if (ch == '#') {
|
||||
ch = stream.lookChar();
|
||||
getName: function Lexer_getName() {
|
||||
var str = '', ch;
|
||||
while ((ch = this.nextChar()) >= 0 && !specialChars[ch]) {
|
||||
if (ch === 0x23) { // '#'
|
||||
ch = this.nextChar();
|
||||
var x = toHexDigit(ch);
|
||||
if (x != -1) {
|
||||
stream.skip();
|
||||
var x2 = toHexDigit(stream.getChar());
|
||||
var x2 = toHexDigit(this.nextChar());
|
||||
if (x2 == -1)
|
||||
error('Illegal digit in hex char in name: ' + x2);
|
||||
str += String.fromCharCode((x << 4) | x2);
|
||||
} else {
|
||||
str += '#';
|
||||
str += ch;
|
||||
str += String.fromCharCode(ch);
|
||||
}
|
||||
} else {
|
||||
str += ch;
|
||||
str += String.fromCharCode(ch);
|
||||
}
|
||||
}
|
||||
if (str.length > 128)
|
||||
if (str.length > 128) {
|
||||
error('Warning: name token is longer than allowed by the spec: ' +
|
||||
str.length);
|
||||
}
|
||||
return new Name(str);
|
||||
},
|
||||
getHexString: function Lexer_getHexString(ch) {
|
||||
getHexString: function Lexer_getHexString() {
|
||||
var str = '';
|
||||
var stream = this.stream;
|
||||
var ch = this.currentChar;
|
||||
var isFirstHex = true;
|
||||
var firstDigit;
|
||||
var secondDigit;
|
||||
while (true) {
|
||||
ch = stream.getChar();
|
||||
if (!ch) {
|
||||
if (ch < 0) {
|
||||
warn('Unterminated hex string');
|
||||
break;
|
||||
} else if (ch === '>') {
|
||||
} else if (ch === 0x3E) { // '>'
|
||||
this.nextChar();
|
||||
break;
|
||||
} else if (specialChars[ch.charCodeAt(0)] === 1) {
|
||||
} else if (specialChars[ch] === 1) {
|
||||
ch = this.nextChar();
|
||||
continue;
|
||||
} else {
|
||||
if (isFirstHex) {
|
||||
firstDigit = toHexDigit(ch);
|
||||
if (firstDigit === -1) {
|
||||
warn('Ignoring invalid character "' + ch + '" in hex string');
|
||||
ch = this.nextChar();
|
||||
continue;
|
||||
}
|
||||
} else {
|
||||
secondDigit = toHexDigit(ch);
|
||||
if (secondDigit === -1) {
|
||||
warn('Ignoring invalid character "' + ch + '" in hex string');
|
||||
ch = this.nextChar();
|
||||
continue;
|
||||
}
|
||||
str += String.fromCharCode((firstDigit << 4) | secondDigit);
|
||||
}
|
||||
isFirstHex = !isFirstHex;
|
||||
ch = this.nextChar();
|
||||
}
|
||||
}
|
||||
return str;
|
||||
|
|
@ -569,73 +580,81 @@ var Lexer = (function LexerClosure() {
|
|||
getObj: function Lexer_getObj() {
|
||||
// skip whitespace and comments
|
||||
var comment = false;
|
||||
var stream = this.stream;
|
||||
var ch;
|
||||
var ch = this.currentChar;
|
||||
while (true) {
|
||||
if (!(ch = stream.getChar()))
|
||||
if (ch < 0) {
|
||||
return EOF;
|
||||
}
|
||||
if (comment) {
|
||||
if (ch == '\r' || ch == '\n')
|
||||
if (ch === 0x0A || ch == 0x0D) // LF, CR
|
||||
comment = false;
|
||||
} else if (ch == '%') {
|
||||
} else if (ch === 0x25) { // '%'
|
||||
comment = true;
|
||||
} else if (specialChars[ch.charCodeAt(0)] != 1) {
|
||||
} else if (specialChars[ch] !== 1) {
|
||||
break;
|
||||
}
|
||||
ch = this.nextChar();
|
||||
}
|
||||
|
||||
// start reading token
|
||||
switch (ch) {
|
||||
case '0': case '1': case '2': case '3': case '4':
|
||||
case '5': case '6': case '7': case '8': case '9':
|
||||
case '+': case '-': case '.':
|
||||
return this.getNumber(ch);
|
||||
case '(':
|
||||
switch (ch | 0) {
|
||||
case 0x30: case 0x31: case 0x32: case 0x33: case 0x34: // '0'-'4'
|
||||
case 0x35: case 0x36: case 0x37: case 0x38: case 0x39: // '5'-'9'
|
||||
case 0x2B: case 0x2D: case 0x2E: // '+', '-', '.'
|
||||
return this.getNumber();
|
||||
case 0x28: // '('
|
||||
return this.getString();
|
||||
case '/':
|
||||
return this.getName(ch);
|
||||
case 0x2F: // '/'
|
||||
return this.getName();
|
||||
// array punctuation
|
||||
case '[':
|
||||
case ']':
|
||||
return Cmd.get(ch);
|
||||
case 0x5B: // '['
|
||||
this.nextChar();
|
||||
return Cmd.get('[');
|
||||
case 0x5D: // ']'
|
||||
this.nextChar();
|
||||
return Cmd.get(']');
|
||||
// hex string or dict punctuation
|
||||
case '<':
|
||||
ch = stream.lookChar();
|
||||
if (ch == '<') {
|
||||
case 0x3C: // '<'
|
||||
ch = this.nextChar();
|
||||
if (ch === 0x3C) {
|
||||
// dict punctuation
|
||||
stream.skip();
|
||||
this.nextChar();
|
||||
return Cmd.get('<<');
|
||||
}
|
||||
return this.getHexString(ch);
|
||||
return this.getHexString();
|
||||
// dict punctuation
|
||||
case '>':
|
||||
ch = stream.lookChar();
|
||||
if (ch == '>') {
|
||||
stream.skip();
|
||||
case 0x3E: // '>'
|
||||
ch = this.nextChar();
|
||||
if (ch === 0x3E) {
|
||||
this.nextChar();
|
||||
return Cmd.get('>>');
|
||||
}
|
||||
return Cmd.get(ch);
|
||||
case '{':
|
||||
case '}':
|
||||
return Cmd.get(ch);
|
||||
// fall through
|
||||
case ')':
|
||||
return Cmd.get('>');
|
||||
case 0x7B: // '{'
|
||||
this.nextChar();
|
||||
return Cmd.get('{');
|
||||
case 0x7D: // '}'
|
||||
this.nextChar();
|
||||
return Cmd.get('}');
|
||||
case 0x29: // ')'
|
||||
error('Illegal character: ' + ch);
|
||||
break;
|
||||
}
|
||||
|
||||
// command
|
||||
var str = ch;
|
||||
var str = String.fromCharCode(ch);
|
||||
var knownCommands = this.knownCommands;
|
||||
var knownCommandFound = knownCommands && (str in knownCommands);
|
||||
while (!!(ch = stream.lookChar()) && !specialChars[ch.charCodeAt(0)]) {
|
||||
while ((ch = this.nextChar()) >= 0 && !specialChars[ch]) {
|
||||
// stop if known command is found and next character does not make
|
||||
// the str a command
|
||||
if (knownCommandFound && !((str + ch) in knownCommands))
|
||||
var possibleCommand = str + String.fromCharCode(ch);
|
||||
if (knownCommandFound && !(possibleCommand in knownCommands)) {
|
||||
break;
|
||||
stream.skip();
|
||||
}
|
||||
if (str.length == 128)
|
||||
error('Command token too long: ' + str.length);
|
||||
str += ch;
|
||||
str = possibleCommand;
|
||||
knownCommandFound = knownCommands && (str in knownCommands);
|
||||
}
|
||||
if (str == 'true')
|
||||
|
|
@ -648,19 +667,20 @@ var Lexer = (function LexerClosure() {
|
|||
},
|
||||
skipToNextLine: function Lexer_skipToNextLine() {
|
||||
var stream = this.stream;
|
||||
while (true) {
|
||||
var ch = stream.getChar();
|
||||
if (!ch || ch == '\n')
|
||||
return;
|
||||
if (ch == '\r') {
|
||||
if ((ch = stream.lookChar()) == '\n')
|
||||
stream.skip();
|
||||
return;
|
||||
var ch = this.currentChar;
|
||||
while (ch >= 0) {
|
||||
if (ch === 0x0D) { // CR
|
||||
ch = this.nextChar();
|
||||
if (ch === 0x0A) { // LF
|
||||
this.nextChar();
|
||||
}
|
||||
break;
|
||||
} else if (ch === 0x0A) { // LF
|
||||
this.nextChar();
|
||||
break;
|
||||
}
|
||||
ch = this.nextChar();
|
||||
}
|
||||
},
|
||||
skip: function Lexer_skip() {
|
||||
this.stream.skip();
|
||||
}
|
||||
};
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue