[408] | 1 | #! /usr/bin/env python |
---|
| 2 | # -*- coding: ISO-8859-15 -*- |
---|
| 3 | # |
---|
| 4 | # pkpgcounter : a generic Page Description Language parser |
---|
| 5 | # |
---|
[443] | 6 | # (c) 2003, 2004, 2005, 2006, 2007 Jerome Alet <alet@librelogiciel.com> |
---|
[463] | 7 | # This program is free software: you can redistribute it and/or modify |
---|
[408] | 8 | # it under the terms of the GNU General Public License as published by |
---|
[463] | 9 | # the Free Software Foundation, either version 3 of the License, or |
---|
[408] | 10 | # (at your option) any later version. |
---|
[463] | 11 | # |
---|
[408] | 12 | # This program is distributed in the hope that it will be useful, |
---|
| 13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
---|
| 15 | # GNU General Public License for more details. |
---|
| 16 | # |
---|
| 17 | # You should have received a copy of the GNU General Public License |
---|
[463] | 18 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
---|
[408] | 19 | # |
---|
| 20 | # $Id$ |
---|
| 21 | # |
---|
| 22 | |
---|
| 23 | """This modules implements a page counter for SPL1 documents.""" |
---|
| 24 | |
---|
| 25 | import sys |
---|
| 26 | import os |
---|
| 27 | import mmap |
---|
| 28 | from struct import unpack |
---|
| 29 | |
---|
| 30 | import pdlparser |
---|
[410] | 31 | import version |
---|
[408] | 32 | |
---|
| 33 | ESCAPECHARS = (chr(0x1b), chr(0x24)) |
---|
| 34 | |
---|
| 35 | class Parser(pdlparser.PDLParser) : |
---|
| 36 | """A parser for SPL1 documents.""" |
---|
| 37 | def isValid(self) : |
---|
[487] | 38 | """Returns True if data is SPL1, else False.""" |
---|
[408] | 39 | if ((self.firstblock[:128].find("\033%-12345X") != -1) and \ |
---|
| 40 | (self.firstblock.find("$PJL ") != -1) and \ |
---|
| 41 | ((self.firstblock.find("LANGUAGE=SMART") != -1) or \ |
---|
| 42 | (self.firstblock.find("LANGUAGE = SMART") != -1))) : |
---|
[487] | 43 | self.logdebug("DEBUG: Input file is in the SPL1 format.") |
---|
[408] | 44 | return True |
---|
| 45 | else : |
---|
| 46 | return False |
---|
| 47 | |
---|
| 48 | def littleEndian(self) : |
---|
| 49 | """Toggles to little endianness.""" |
---|
| 50 | self.unpackType = { 1 : "B", 2 : "<H", 4 : "<I" } |
---|
| 51 | self.unpackShort = self.unpackType[2] |
---|
| 52 | self.unpackLong = self.unpackType[4] |
---|
| 53 | return 0 |
---|
| 54 | |
---|
| 55 | def bigEndian(self) : |
---|
| 56 | """Toggles to big endianness.""" |
---|
| 57 | self.unpackType = { 1 : "B", 2 : ">H", 4 : ">I" } |
---|
| 58 | self.unpackShort = self.unpackType[2] |
---|
| 59 | self.unpackLong = self.unpackType[4] |
---|
| 60 | return 0 |
---|
| 61 | |
---|
| 62 | def escape(self, nextpos) : |
---|
| 63 | """Handles the ESC code.""" |
---|
[409] | 64 | self.isbitmap = False |
---|
[408] | 65 | pos = endpos = nextpos |
---|
| 66 | minfile = self.minfile |
---|
| 67 | if minfile[pos : pos+8] == r"%-12345X" : |
---|
| 68 | endpos = pos + 9 |
---|
| 69 | elif minfile[pos-1] in ESCAPECHARS : |
---|
| 70 | endpos = pos |
---|
| 71 | else : |
---|
| 72 | return 0 |
---|
| 73 | endmark = (chr(0x1b), chr(0x00)) |
---|
| 74 | asciilimit = chr(0x80) |
---|
| 75 | quotes = 0 |
---|
| 76 | while (minfile[endpos] not in endmark) and \ |
---|
| 77 | ((minfile[endpos] < asciilimit) or (quotes % 2)) : |
---|
| 78 | if minfile[endpos] == '"' : |
---|
| 79 | quotes += 1 |
---|
| 80 | endpos += 1 |
---|
| 81 | |
---|
| 82 | # Store this in a per page mapping. |
---|
| 83 | # NB : First time will be at page 0 (i.e. **before** page 1) ! |
---|
| 84 | stuff = self.escapedStuff.setdefault(self.pagecount, []) |
---|
[409] | 85 | datas = minfile[pos-1 : endpos] |
---|
| 86 | stuff.append(datas) |
---|
| 87 | if datas.endswith("$PJL BITMAP START\r\n") : |
---|
| 88 | self.isbitmap = True |
---|
| 89 | self.logdebug("Escaped datas : [%s]" % repr(datas)) |
---|
[408] | 90 | return endpos - pos + 1 |
---|
| 91 | |
---|
| 92 | def getJobSize(self) : |
---|
| 93 | """Counts pages in an SPL1 document. |
---|
| 94 | |
---|
| 95 | Algorithm by Jerome Alet. |
---|
| 96 | """ |
---|
| 97 | infileno = self.infile.fileno() |
---|
[409] | 98 | self.minfile = minfile = mmap.mmap(infileno, os.fstat(infileno)[6], prot=mmap.PROT_READ, flags=mmap.MAP_SHARED) |
---|
[408] | 99 | self.pagecount = 0 |
---|
| 100 | self.escapedStuff = {} # For escaped datas, mostly PJL commands |
---|
| 101 | self.bigEndian() |
---|
| 102 | |
---|
[409] | 103 | self.isbitmap = False |
---|
[408] | 104 | pos = 0 |
---|
| 105 | try : |
---|
| 106 | try : |
---|
| 107 | while 1 : |
---|
[409] | 108 | tag = minfile[pos] |
---|
[408] | 109 | if tag in ESCAPECHARS : |
---|
| 110 | pos += self.escape(pos+1) |
---|
| 111 | else : |
---|
[409] | 112 | if not self.isbitmap : |
---|
[410] | 113 | raise pdlparser.PDLParserError, "Unfortunately SPL1 is incompletely recognized. Parsing aborted. Please report the problem to %s" % version.__authoremail__ |
---|
[409] | 114 | offset = unpack(self.unpackLong, minfile[pos:pos+4])[0] |
---|
| 115 | sequencenum = unpack(self.unpackShort, minfile[pos+4:pos+6])[0] |
---|
| 116 | codesop = " ".join([ "%02x" % ord(v) for v in minfile[pos+6:pos+12]]) |
---|
| 117 | if codesop != "06 00 00 80 13 40" : |
---|
[410] | 118 | raise pdlparser.PDLParserError, "Unfortunately SPL1 is incompletely recognized. Parsing aborted. Please report the problem to %s" % version.__authoremail__ |
---|
[409] | 119 | if not sequencenum : |
---|
| 120 | self.pagecount += 1 |
---|
[408] | 121 | pos += 4 + offset |
---|
| 122 | except IndexError : # EOF ? |
---|
| 123 | pass |
---|
| 124 | finally : |
---|
[409] | 125 | minfile.close() |
---|
[408] | 126 | return self.pagecount |
---|
| 127 | |
---|
| 128 | if __name__ == "__main__" : |
---|
[415] | 129 | pdlparser.test(Parser) |
---|