fix CMapDB initialization stuff. more code cleanup.

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@148 1aa58f4a-7d42-0410-adbc-911cccaed67c

TODO

@@ -4,3 +4,4 @@ TODOs:
   - Better API Documentation.
   - Robust error handling.
   - Any special handling for linearized PDFs?
+  - Handle security handler. (I need more samples!)

pdfminer/cmap.py

@@ -4,20 +4,14 @@ import re
 import os
 import os.path
 from sys import stderr
-from struct import pack
-from struct import unpack
+from struct import pack, unpack
+from psparser import PSStackParser
+from psparser import PSException, PSSyntaxError, PSTypeError, PSEOF
+from psparser import PSLiteral, PSKeyword
+from psparser import literal_name, keyword_name
 from fontmetrics import FONT_METRICS
 from latin_enc import ENCODING
 from glyphlist import charname2unicode
-from psparser import PSException
-from psparser import PSSyntaxError
-from psparser import PSTypeError
-from psparser import PSEOF
-from psparser import PSLiteral
-from psparser import PSKeyword
-from psparser import literal_name
-from psparser import keyword_name
-from psparser import PSStackParser
 from utils import choplist
 from utils import nunpack
 try:
@@ -201,36 +195,30 @@ class CMapDB(object):
 
     class CMapNotFound(CMapError): pass
 
-    CMAP_ALIAS = {
-      }
-
+    CMAP_ALIAS = { }
     debug = 0
-    dirname = None
-    cdbdirname = None
-    cmapdb = {}
 
-    @classmethod
-    def initialize(klass, dirname=None, cdbdirname=None):
+    def __init__(self, dirname=None, cdbdirname=None):
         if not dirname:
             dirname = find_cmap_path()
-        klass.dirname = dirname
-        klass.cdbdirname = cdbdirname or dirname
+        self.dirname = dirname
+        self.cdbdirname = cdbdirname or dirname
+        self.cmapdb = {}
         return
 
-    @classmethod
-    def get_cmap(klass, cmapname, strict=True):
-        cmapname = klass.CMAP_ALIAS.get(cmapname, cmapname)
-        if cmapname in klass.cmapdb:
-            cmap = klass.cmapdb[cmapname]
+    def get_cmap(self, cmapname, strict=True):
+        cmapname = self.CMAP_ALIAS.get(cmapname, cmapname)
+        if cmapname in self.cmapdb:
+            cmap = self.cmapdb[cmapname]
         else:
-            fname = os.path.join(klass.dirname, cmapname)
-            cdbname = os.path.join(klass.cdbdirname, cmapname+'.cmap.cdb')
+            fname = os.path.join(self.dirname, cmapname)
+            cdbname = os.path.join(self.cdbdirname, cmapname+'.cmap.cdb')
             if os.path.exists(cdbname):
-                if 1 <= klass.debug:
+                if 1 <= self.debug:
                     print >>stderr, 'Opening: CDBCMap %r...' % cdbname
                 cmap = CDBCMap(cdbname)
             elif os.path.exists(fname):
-                if 1 <= klass.debug:
+                if 1 <= self.debug:
                     print >>stderr, 'Reading: CMap %r...' % fname
                 cmap = CMap()
                 fp = file(fname, 'rb')
@@ -240,7 +228,7 @@ class CMapDB(object):
                 cmap = CMap() # just create empty cmap
             else:
                 raise CMapDB.CMapNotFound(cmapname)
-            klass.cmapdb[cmapname] = cmap
+            self.cmapdb[cmapname] = cmap
         return cmap
 
 

pdfminer/converter.py

@@ -1,20 +1,12 @@
 #!/usr/bin/env python
 import sys
-from pdfdevice import PDFDevice
-from pdfdevice import PDFTextDevice
+from pdfdevice import PDFDevice, PDFTextDevice
 from pdffont import PDFUnicodeNotDefined
 from layout import LayoutContainer
-from layout import LTPage
-from layout import LTText
-from layout import LTLine
-from layout import LTRect
-from layout import LTFigure
-from layout import LTTextItem
-from layout import LTTextBox
-from layout import LTTextLine
-from utils import apply_matrix_pt
-from utils import mult_matrix
+from layout import LTPage, LTText, LTLine, LTRect
+from layout import LTFigure, LTTextItem, LTTextBox, LTTextLine
 from utils import enc
+from utils import apply_matrix_pt, mult_matrix
 
 
 ##  TagExtractor

pdfminer/pdffont.py

@@ -1,33 +1,19 @@
 #!/usr/bin/env python
 import sys
-from cmap import CMap
-from cmap import CMapDB
-from cmap import CMapParser
-from cmap import FontMetricsDB
-from cmap import EncodingDB
-from struct import pack
-from struct import unpack
-from psparser import PSLiteralTable
-from psparser import PSKeywordTable
-from psparser import PSLiteral
-from psparser import literal_name
-from psparser import keyword_name
-from psparser import STRICT
-from pdftypes import PDFException
-from pdftypes import resolve1
-from pdftypes import int_value
-from pdftypes import float_value
-from pdftypes import num_value
-from pdftypes import str_value
-from pdftypes import list_value
-from pdftypes import dict_value
-from pdftypes import stream_value
-from utils import apply_matrix_norm
-from utils import nunpack
 try:
     from cStringIO import StringIO
 except ImportError:
     from StringIO import StringIO
+from cmap import CMap, CMapDB, CMapParser
+from cmap import FontMetricsDB, EncodingDB
+from struct import pack, unpack
+from psparser import STRICT
+from psparser import PSLiteralTable, PSKeywordTable
+from psparser import PSLiteral, literal_name, keyword_name
+from pdftypes import PDFException, resolve1
+from pdftypes import int_value, float_value, num_value
+from pdftypes import str_value, list_value, dict_value, stream_value
+from utils import apply_matrix_norm, nunpack
 
 
 ##  CFFFont

pdfminer/pdfinterp.py

@@ -7,43 +7,26 @@ try:
 except ImportError:
     from StringIO import StringIO
 from cmap import CMapDB
-from psparser import PSException
-from psparser import PSTypeError
-from psparser import PSEOF
-from psparser import PSLiteralTable
-from psparser import PSKeywordTable
-from psparser import literal_name
-from psparser import keyword_name
+from psparser import PSException, PSTypeError, PSEOF
+from psparser import PSLiteralTable, PSKeywordTable
+from psparser import PSKeyword, literal_name, keyword_name
 from psparser import PSStackParser
-from psparser import PSKeyword
 from psparser import STRICT
-from pdftypes import PDFException
-from pdftypes import PDFStream
-from pdftypes import PDFObjRef
+from pdftypes import PDFException, PDFStream, PDFObjRef
 from pdftypes import resolve1
-from pdftypes import int_value
-from pdftypes import float_value
-from pdftypes import num_value
-from pdftypes import str_value
-from pdftypes import list_value
-from pdftypes import dict_value
-from pdftypes import stream_value
+from pdftypes import int_value, float_value, num_value
+from pdftypes import str_value, list_value, dict_value, stream_value
 from pdffont import PDFFontError
-from pdffont import PDFType1Font
-from pdffont import PDFTrueTypeFont
-from pdffont import PDFType3Font
+from pdffont import PDFType1Font, PDFTrueTypeFont, PDFType3Font
 from pdffont import PDFCIDFont
-from pdfparser import PDFDocument
-from pdfparser import PDFParser
+from pdfparser import PDFDocument, PDFParser
 from pdfparser import PDFPasswordIncorrect
 from pdfcolor import PDFColorSpace
 from pdfcolor import PREDEFINED_COLORSPACE
-from pdfcolor import LITERAL_DEVICE_GRAY
-from pdfcolor import LITERAL_DEVICE_RGB
+from pdfcolor import LITERAL_DEVICE_GRAY, LITERAL_DEVICE_RGB
 from pdfcolor import LITERAL_DEVICE_CMYK
 from utils import choplist
-from utils import mult_matrix
-from utils import MATRIX_IDENTITY
+from utils import mult_matrix, MATRIX_IDENTITY
 
 
 ##  Exceptions
@@ -124,8 +107,9 @@ class PDFResourceManager(object):
     '''
     debug = 0
 
-    def __init__(self):
+    def __init__(self, cmapdb):
         self.fonts = {}
+        self.cmapdb = cmapdb
         return
 
     def get_procset(self, procs):
@@ -140,7 +124,7 @@ class PDFResourceManager(object):
         return
 
     def get_cmap(self, cmapname, strict=False):
-        return CMapDB.get_cmap(cmapname, strict=strict)
+        return self.cmapdb.get_cmap(cmapname, strict=strict)
 
     def get_font(self, objid, spec):
         if objid and objid in self.fonts:

pdfminer/pdfparser.py

@@ -4,32 +4,19 @@ import re
 import md5
 import struct
 from sys import stderr
-from utils import choplist
-from utils import nunpack
-from utils import decode_text
-from arcfour import Arcfour
 from psparser import PSStackParser
-from psparser import PSSyntaxError
-from psparser import PSEOF
-from psparser import PSLiteralTable
-from psparser import PSKeywordTable
-from psparser import literal_name
-from psparser import keyword_name
+from psparser import PSSyntaxError, PSEOF
+from psparser import PSLiteralTable, PSKeywordTable
+from psparser import literal_name, keyword_name
 from psparser import STRICT
-from pdftypes import PDFException
-from pdftypes import PDFTypeError
-from pdftypes import PDFNotImplementedError
-from pdftypes import PDFStream
-from pdftypes import PDFObjRef
-from pdftypes import resolve1
-from pdftypes import decipher_all
-from pdftypes import int_value
-from pdftypes import float_value
-from pdftypes import num_value
-from pdftypes import str_value
-from pdftypes import list_value
-from pdftypes import dict_value
-from pdftypes import stream_value
+from pdftypes import PDFException, PDFTypeError, PDFNotImplementedError
+from pdftypes import PDFStream, PDFObjRef
+from pdftypes import resolve1, decipher_all
+from pdftypes import int_value, float_value, num_value
+from pdftypes import str_value, list_value, dict_value, stream_value
+from arcfour import Arcfour
+from utils import choplist, nunpack
+from utils import decode_text
 
 
 ##  Exceptions

pdfminer/pdftypes.py

@@ -3,13 +3,9 @@ import sys
 import zlib
 from lzw import LZWDecoder
 from psparser import PSException
-from psparser import PSObject
-from psparser import PSLiteral
-from psparser import PSKeyword
-from psparser import PSLiteralTable
-from psparser import PSKeywordTable
-from psparser import literal_name
-from psparser import keyword_name
+from psparser import PSObject, PSLiteral, PSKeyword
+from psparser import PSLiteralTable, PSKeywordTable
+from psparser import literal_name, keyword_name
 from psparser import STRICT
 
 LITERAL_CRYPT = PSLiteralTable.intern('Crypt')

pdfminer/pycdb.py

@@ -8,8 +8,7 @@
 
 import sys
 import os
-from struct import pack
-from struct import unpack
+from struct import pack, unpack
 from array import array
 
 

pdfminer/rijndael.py

@@ -7,8 +7,7 @@
 ##  http://www.efgh.com/software/rijndael.htm
 ##
 import sys
-from struct import pack
-from struct import unpack
+from struct import pack, unpack
 
 def KEYLENGTH(keybits): return (keybits)/8
 def RKLENGTH(keybits): return (keybits)/8+28

samples/Makefile

@@ -45,7 +45,7 @@ clean:
 
 test: htmls texts xmls
 htmls: $(HTMLS)
-tests: $(TEXTS)
+texts: $(TEXTS)
 xmls: $(XMLS)
 
 .SUFFIXES: .pdf .html .xml .txt

tools/pdf2txt.py

@@ -58,8 +58,8 @@ def main(argv):
     PDFPageInterpreter.debug = debug
     PDFDevice.debug = debug
     #
-    CMapDB.initialize(cmapdir)
-    rsrc = PDFResourceManager()
+    cmapdb = CMapDB(cmapdir)
+    rsrc = PDFResourceManager(cmapdb)
     if not outtype:
         outtype = 'text'
         if outfile: