diff --git a/README.html b/README.html
index 0e6418b..709476d 100644
--- a/README.html
+++ b/README.html
@@ -14,7 +14,7 @@ Python PDF parser and analyzer
-Last Modified: Mon Feb 2 00:01:01 JST 2009
+Last Modified: Wed Mar 25 01:26:33 JST 2009
@@ -175,6 +175,10 @@ By default, it extracts texts from all the pages.
-c codec
Specifies the output codec for non-ASCII texts.
+
-w
+ Split each word into a different chunk in the output.
+This makes the word spacing correctly handled.
+
-t type
Specifies the output format. The following formats are currently supported.
@@ -250,6 +254,7 @@ no stream header is displayed for the ease of saving it to a file.
Changes
+- 2009/03/25: Encoding problems fixed. Word splitting option added.
- 2009/02/01: Various bugfixes. Thanks to Hiroshi Manabe.
- 2009/01/17: Handling a trailer correctly that contains both /XrefStm and /Prev entries.
- 2009/01/10: Handling Type3 font metrics correctly.
diff --git a/pdflib/cmap.py b/pdflib/cmap.py
index bcdd9e9..1c8ab53 100644
--- a/pdflib/cmap.py
+++ b/pdflib/cmap.py
@@ -1,5 +1,5 @@
#!/usr/bin/env python
-import sys
+import sys, re
stderr = sys.stderr
from struct import pack, unpack
from utils import choplist, nunpack
@@ -15,6 +15,16 @@ except ImportError:
class CMapError(Exception): pass
+STRIP_NAME = re.compile(r'[0-9]+')
+def name2unicode(name):
+ from glyphlist import charname2unicode
+ if name in charname2unicode:
+ return charname2unicode[name]
+ m = STRIP_NAME.search(name)
+ if not m: raise KeyError(name)
+ return int(m.group(0))
+
+
## CMap
##
class CMap(object):
@@ -48,10 +58,9 @@ class CMap(object):
return self
def register_cid2code(self, cid, code):
- from glyphlist import charname2unicode
if isinstance(cid, int):
if isinstance(code, PSLiteral):
- self.cid2code[cid] = pack('>H', charname2unicode[code.name])
+ self.cid2code[cid] = pack('>H', name2unicode(code.name))
elif isinstance(code, str):
self.cid2code[cid] = code
return self
@@ -352,7 +361,6 @@ class FontMetricsDB(object):
##
class EncodingDB(object):
- from glyphlist import charname2unicode
from latin_enc import ENCODING
std2unicode = {}
@@ -360,7 +368,7 @@ class EncodingDB(object):
win2unicode = {}
pdf2unicode = {}
for (name,std,mac,win,pdf) in ENCODING:
- c = unichr(charname2unicode[name])
+ c = unichr(name2unicode(name))
if std: std2unicode[std] = c
if mac: mac2unicode[mac] = c
if win: win2unicode[win] = c
@@ -384,7 +392,7 @@ class EncodingDB(object):
cid = x
elif isinstance(x, PSLiteral):
try:
- cid2unicode[cid] = unichr(EncodingDB.charname2unicode[x.name])
+ cid2unicode[cid] = unichr(name2unicode(x.name))
except KeyError:
pass
cid += 1
diff --git a/pdflib/pdffont.py b/pdflib/pdffont.py
index 5735f05..d1f2d0d 100644
--- a/pdflib/pdffont.py
+++ b/pdflib/pdffont.py
@@ -15,51 +15,135 @@ from cmap import CMap, CMapDB, CMapParser, FontMetricsDB, EncodingDB
from utils import apply_matrix_norm, nunpack
-NIBBLES = ('0','1','2','3','4','5','6','7','8','9','.','e','e-',None,'-')
-def getnum(fp):
- b0 = ord(fp.read(1))
- if b0 == 30:
- s = ''
- loop = True
- while loop:
- b = ord(fp.read(1))
- for n in (b >> 4, b & 15):
- if n == 15:
- loop = False
- else:
- s += NIBBLES[n]
- return float(s)
- if 32 <= b0 and b0 <= 246:
- return b0-139
- b1 = ord(fp.read(1))
- if 247 <= b0 and b0 <= 250:
- return ((b0-247)<<8)+b1+108
- if 251 <= b0 and b0 <= 254:
- return -((b0-251)<<8)-b1-108
- b2 = ord(fp.read(1))
- if 128 <= b1: b1 -= 256
- if b0 == 28:
- return b1<<8 | b2
- return b1<<24 | b2<<16 | unpack('>H',fp.read(2))[0]
-#assert getop(StringIO('\x8b')) == 0
-#assert getop(StringIO('\xef')) == 100
-#assert getop(StringIO('\x27')) == -100
-#assert getop(StringIO('\xfa\x7c')) == 1000
-#assert getop(StringIO('\xfe\x7c')) == -1000
-#assert getop(StringIO('\x1c\x27\x10')) == 10000
-#assert getop(StringIO('\x1c\xd8\xf0')) == -10000
-#assert getop(StringIO('\x1d\x00\x01\x86\xa0')) == 100000
-#assert getop(StringIO('\x1d\xff\xfe\x79\x60')) == -100000
-#assert getop(StringIO('\x1e\xe2\xa2\x5f')) == -2.25
-#assert getop(StringIO('\x1e\x0a\x14\x05\x41\xc3\xff')) == 0.140541e-3
-
-
## CFFFont
## (Format specified in Adobe Technical Note: #5176
## "The Compact Font Format Specification")
##
+NIBBLES = ('0','1','2','3','4','5','6','7','8','9','.','e','e-',None,'-')
+def getdict(data):
+ d = {}
+ fp = StringIO(data)
+ stack = []
+ while 1:
+ c = fp.read(1)
+ if not c: break
+ b0 = ord(c)
+ if b0 <= 21:
+ d[b0] = stack
+ stack = []
+ continue
+ if b0 == 30:
+ s = ''
+ loop = True
+ while loop:
+ b = ord(fp.read(1))
+ for n in (b >> 4, b & 15):
+ if n == 15:
+ loop = False
+ else:
+ s += NIBBLES[n]
+ value = float(s)
+ elif 32 <= b0 and b0 <= 246:
+ value = b0-139
+ else:
+ b1 = ord(fp.read(1))
+ if 247 <= b0 and b0 <= 250:
+ value = ((b0-247)<<8)+b1+108
+ elif 251 <= b0 and b0 <= 254:
+ value = -((b0-251)<<8)-b1-108
+ else:
+ b2 = ord(fp.read(1))
+ if 128 <= b1: b1 -= 256
+ if b0 == 28:
+ value = b1<<8 | b2
+ else:
+ value = b1<<24 | b2<<16 | unpack('>H', fp.read(2))[0]
+ stack.append(value)
+ return d
+
class CFFFont(object):
+ STANDARD_STRINGS = (
+ '.notdef', 'space', 'exclam', 'quotedbl', 'numbersign',
+ 'dollar', 'percent', 'ampersand', 'quoteright', 'parenleft',
+ 'parenright', 'asterisk', 'plus', 'comma', 'hyphen', 'period',
+ 'slash', 'zero', 'one', 'two', 'three', 'four', 'five', 'six',
+ 'seven', 'eight', 'nine', 'colon', 'semicolon', 'less', 'equal',
+ 'greater', 'question', 'at', 'A', 'B', 'C', 'D', 'E', 'F', 'G',
+ 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T',
+ 'U', 'V', 'W', 'X', 'Y', 'Z', 'bracketleft', 'backslash',
+ 'bracketright', 'asciicircum', 'underscore', 'quoteleft', 'a',
+ 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
+ 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
+ 'braceleft', 'bar', 'braceright', 'asciitilde', 'exclamdown',
+ 'cent', 'sterling', 'fraction', 'yen', 'florin', 'section',
+ 'currency', 'quotesingle', 'quotedblleft', 'guillemotleft',
+ 'guilsinglleft', 'guilsinglright', 'fi', 'fl', 'endash',
+ 'dagger', 'daggerdbl', 'periodcentered', 'paragraph', 'bullet',
+ 'quotesinglbase', 'quotedblbase', 'quotedblright',
+ 'guillemotright', 'ellipsis', 'perthousand', 'questiondown',
+ 'grave', 'acute', 'circumflex', 'tilde', 'macron', 'breve',
+ 'dotaccent', 'dieresis', 'ring', 'cedilla', 'hungarumlaut',
+ 'ogonek', 'caron', 'emdash', 'AE', 'ordfeminine', 'Lslash',
+ 'Oslash', 'OE', 'ordmasculine', 'ae', 'dotlessi', 'lslash',
+ 'oslash', 'oe', 'germandbls', 'onesuperior', 'logicalnot', 'mu',
+ 'trademark', 'Eth', 'onehalf', 'plusminus', 'Thorn',
+ 'onequarter', 'divide', 'brokenbar', 'degree', 'thorn',
+ 'threequarters', 'twosuperior', 'registered', 'minus', 'eth',
+ 'multiply', 'threesuperior', 'copyright', 'Aacute',
+ 'Acircumflex', 'Adieresis', 'Agrave', 'Aring', 'Atilde',
+ 'Ccedilla', 'Eacute', 'Ecircumflex', 'Edieresis', 'Egrave',
+ 'Iacute', 'Icircumflex', 'Idieresis', 'Igrave', 'Ntilde',
+ 'Oacute', 'Ocircumflex', 'Odieresis', 'Ograve', 'Otilde',
+ 'Scaron', 'Uacute', 'Ucircumflex', 'Udieresis', 'Ugrave',
+ 'Yacute', 'Ydieresis', 'Zcaron', 'aacute', 'acircumflex',
+ 'adieresis', 'agrave', 'aring', 'atilde', 'ccedilla', 'eacute',
+ 'ecircumflex', 'edieresis', 'egrave', 'iacute', 'icircumflex',
+ 'idieresis', 'igrave', 'ntilde', 'oacute', 'ocircumflex',
+ 'odieresis', 'ograve', 'otilde', 'scaron', 'uacute',
+ 'ucircumflex', 'udieresis', 'ugrave', 'yacute', 'ydieresis',
+ 'zcaron', 'exclamsmall', 'Hungarumlautsmall', 'dollaroldstyle',
+ 'dollarsuperior', 'ampersandsmall', 'Acutesmall',
+ 'parenleftsuperior', 'parenrightsuperior', 'twodotenleader',
+ 'onedotenleader', 'zerooldstyle', 'oneoldstyle', 'twooldstyle',
+ 'threeoldstyle', 'fouroldstyle', 'fiveoldstyle', 'sixoldstyle',
+ 'sevenoldstyle', 'eightoldstyle', 'nineoldstyle',
+ 'commasuperior', 'threequartersemdash', 'periodsuperior',
+ 'questionsmall', 'asuperior', 'bsuperior', 'centsuperior',
+ 'dsuperior', 'esuperior', 'isuperior', 'lsuperior', 'msuperior',
+ 'nsuperior', 'osuperior', 'rsuperior', 'ssuperior', 'tsuperior',
+ 'ff', 'ffi', 'ffl', 'parenleftinferior', 'parenrightinferior',
+ 'Circumflexsmall', 'hyphensuperior', 'Gravesmall', 'Asmall',
+ 'Bsmall', 'Csmall', 'Dsmall', 'Esmall', 'Fsmall', 'Gsmall',
+ 'Hsmall', 'Ismall', 'Jsmall', 'Ksmall', 'Lsmall', 'Msmall',
+ 'Nsmall', 'Osmall', 'Psmall', 'Qsmall', 'Rsmall', 'Ssmall',
+ 'Tsmall', 'Usmall', 'Vsmall', 'Wsmall', 'Xsmall', 'Ysmall',
+ 'Zsmall', 'colonmonetary', 'onefitted', 'rupiah', 'Tildesmall',
+ 'exclamdownsmall', 'centoldstyle', 'Lslashsmall', 'Scaronsmall',
+ 'Zcaronsmall', 'Dieresissmall', 'Brevesmall', 'Caronsmall',
+ 'Dotaccentsmall', 'Macronsmall', 'figuredash', 'hypheninferior',
+ 'Ogoneksmall', 'Ringsmall', 'Cedillasmall', 'questiondownsmall',
+ 'oneeighth', 'threeeighths', 'fiveeighths', 'seveneighths',
+ 'onethird', 'twothirds', 'zerosuperior', 'foursuperior',
+ 'fivesuperior', 'sixsuperior', 'sevensuperior', 'eightsuperior',
+ 'ninesuperior', 'zeroinferior', 'oneinferior', 'twoinferior',
+ 'threeinferior', 'fourinferior', 'fiveinferior', 'sixinferior',
+ 'seveninferior', 'eightinferior', 'nineinferior',
+ 'centinferior', 'dollarinferior', 'periodinferior',
+ 'commainferior', 'Agravesmall', 'Aacutesmall',
+ 'Acircumflexsmall', 'Atildesmall', 'Adieresissmall',
+ 'Aringsmall', 'AEsmall', 'Ccedillasmall', 'Egravesmall',
+ 'Eacutesmall', 'Ecircumflexsmall', 'Edieresissmall',
+ 'Igravesmall', 'Iacutesmall', 'Icircumflexsmall',
+ 'Idieresissmall', 'Ethsmall', 'Ntildesmall', 'Ogravesmall',
+ 'Oacutesmall', 'Ocircumflexsmall', 'Otildesmall',
+ 'Odieresissmall', 'OEsmall', 'Oslashsmall', 'Ugravesmall',
+ 'Uacutesmall', 'Ucircumflexsmall', 'Udieresissmall',
+ 'Yacutesmall', 'Thornsmall', 'Ydieresissmall', '001.000',
+ '001.001', '001.002', '001.003', 'Black', 'Bold', 'Book',
+ 'Light', 'Medium', 'Regular', 'Roman', 'Semibold',
+ )
+
class INDEX(object):
def __init__(self, fp):
@@ -82,11 +166,13 @@ class CFFFont(object):
self.fp.seek(self.base+self.offsets[i])
return self.fp.read(self.offsets[i+1]-self.offsets[i])
- def __init__(self, name, fp):
- self.name = name
- self.fp = fp
+ def __iter__(self):
+ return iter( self[i] for i in xrange(len(self)) )
+
+ def __init__(self, fp0):
+ self.fp = fp0
# Header
- (_major,_minor,hdrsize,self.offsize) = unpack('BBBB', fp.read(4))
+ (_major,_minor,hdrsize,self.offsize) = unpack('BBBB', self.fp.read(4))
self.fp.read(hdrsize-4)
# Name INDEX
self.name_index = self.INDEX(self.fp)
@@ -96,11 +182,55 @@ class CFFFont(object):
self.string_index = self.INDEX(self.fp)
# Global Subr INDEX
self.subr_index = self.INDEX(self.fp)
+ # Top DICT DATA
+ self.top_dict = getdict(self.dict_index[0])
+ (charset_pos,) = self.top_dict.get(15, 0)
+ (encoding_pos,) = self.top_dict.get(16, 0)
+ (charstring_pos,) = self.top_dict.get(17, 0)
+ # CharStrings
+ self.fp.seek(charstring_pos)
+ self.charstring = self.INDEX(self.fp)
+ self.nglyphs = len(self.charstring)
# Encodings
+ self.code2gid = {}
+ self.gid2code = {}
+ self.fp.seek(encoding_pos)
+ format = self.fp.read(1)
+ if format == '\x00':
+ # Format 0
+ (n,) = unpack('B', self.fp.read(1))
+ for (code,gid) in enumerate(unpack('B'*n, self.fp.read(n))):
+ self.code2gid[code] = gid
+ self.gid2code[gid] = code
+ else:
+ # Format 1
+ assert 0
# Charsets
+ self.name2gid = {}
+ self.gid2name = {}
+ self.fp.seek(charset_pos)
+ format = self.fp.read(1)
+ if format == '\x00':
+ # Format 0
+ n = self.nglyphs-1
+ for (gid,sid) in enumerate(unpack('>'+'H'*n, self.fp.read(2*n))):
+ gid += 1
+ name = self.getstr(sid)
+ self.name2gid[name] = gid
+ self.gid2name[gid] = name
+ else:
+ # Format 1
+ assert 0
+ #print self.code2gid
+ #print self.name2gid
+ #assert 0
return
-
+ def getstr(self, sid):
+ if sid < len(self.STANDARD_STRINGS):
+ return self.STANDARD_STRINGS[sid]
+ return self.string_index[sid-len(self.STANDARD_STRINGS)]
+
## TrueTypeFont
##
@@ -184,6 +314,7 @@ class PDFFontError(PDFException): pass
class PDFUnicodeNotDefined(PDFFontError): pass
LITERAL_STANDARD_ENCODING = PSLiteralTable.intern('StandardEncoding')
+LITERAL_TYPE1C = PSLiteralTable.intern('Type1C')
# PDFFont
@@ -449,7 +580,7 @@ class PDFCIDFont(PDFFont):
def main(argv):
for fname in argv[1:]:
fp = file(fname, 'rb')
- CFFFont(fname, fp)
+ CFFFont(fp)
fp.close()
return
if __name__ == '__main__': sys.exit(main(sys.argv))
diff --git a/tools/dumppdf.py b/tools/dumppdf.py
index 8eae1fe..61b2aef 100755
--- a/tools/dumppdf.py
+++ b/tools/dumppdf.py
@@ -13,7 +13,7 @@ stdout = sys.stdout
stderr = sys.stderr
-ESC_PAT = re.compile(r'[\000-\037&<>\042\047\134\177-\377]')
+ESC_PAT = re.compile(r'[\000-\037&<>()\042\047\134\177-\377]')
def esc(s):
return ESC_PAT.sub(lambda m:'%d;' % ord(m.group(0)), s)