renamed cmap.py -> cmapdb.py (avoiding future name changes)

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@161 1aa58f4a-7d42-0410-adbc-911cccaed67c

docs/index.html

@@ -19,7 +19,7 @@ Python PDF parser and analyzer
 
 <div align=right class=lastmod>
 <!-- hhmts start -->
-Last Modified: Sun Nov 29 16:16:28 JST 2009
+Last Modified: Sun Nov 29 16:20:36 JST 2009
 <!-- hhmts end -->
 </div>
 
@@ -65,10 +65,10 @@ PDF parser that can be used for other purposes instead of text analysis.
 
 <a name="source"></a>
 <p>
-<strong>Download:</strong><br>
+<strong>Download from PyPI:</strong><br>
-<a href="http://pypi.python.org/packages/source/p/pdfminer/pdfminer-20091129.tar.gz">pdfminer-20091129.tar.gz</a>
+<a href="http://pypi.python.org/pypi/pdfminer/">
+http://pypi.python.org/pypi/pdfminer/
 </a>
-(1.8Mbytes)
 
 <p>
 <strong>Discussion:</strong> (for questions and comments, post here)<br>

pdfminer/cmapdb.py

@@ -235,7 +235,7 @@ class CMapDB(object):
                     print >>sys.stderr, 'Reading: CMap %r...' % fname
                 cmap = CMap()
                 fp = file(fname, 'rb')
-                CMapParser(cmap, fp).run()
+                CMapParser(self, cmap, fp).run()
                 fp.close()
             elif not strict:
                 cmap = CMap() # just create empty cmap
@@ -249,8 +249,9 @@ class CMapDB(object):
 ##
 class CMapParser(PSStackParser):
 
-    def __init__(self, cmap, fp):
+    def __init__(self, cmapdb, cmap, fp):
         PSStackParser.__init__(self, fp)
+        self.cmapdb = cmapdb
         self.cmap = cmap
         self.in_cmap = False
         return
@@ -282,11 +283,12 @@ class CMapParser(PSStackParser):
             return
 
         if name == 'usecmap':
-            try:
+            if self.cmapdb:
-                ((_,cmapname),) = self.pop(1)
+                try:
-                self.cmap.copycmap(CMapDB.get_cmap(literal_name(cmapname)))
+                    ((_,cmapname),) = self.pop(1)
-            except PSSyntaxError:
+                    self.cmap.copycmap(self.cmapdb.get_cmap(literal_name(cmapname)))
-                pass
+                except PSSyntaxError:
+                    pass
             return
 
         if name == 'begincodespacerange':
@@ -440,7 +442,7 @@ def dump_cdb(cmap, cdbfile, verbose=1):
 
 def convert_cmap(cmapdir, outputdir, force=False):
     """Convert all CMap source files in a directory into cdb files."""
-    CMapDB.initialize(cmapdir)
+    cmapdb = CMapDB(cmapdir)
     for fname in os.listdir(cmapdir):
         if '.' in fname: continue
         cmapname = os.path.basename(fname)
@@ -449,7 +451,7 @@ def convert_cmap(cmapdir, outputdir, force=False):
             print >>sys.stderr, 'Skipping: %r' % cmapname
             continue
         print >>sys.stderr, 'Reading: %r...' % cmapname
-        cmap = CMapDB.get_cmap(cmapname)
+        cmap = cmapdb.get_cmap(cmapname)
         dump_cdb(cmap, cdbname)
     return
 

pdfminer/pdffont.py

@@ -4,8 +4,8 @@ try:
     from cStringIO import StringIO
 except ImportError:
     from StringIO import StringIO
-from cmap import CMap, CMapDB, CMapParser
+from cmapdb import CMap, CMapDB, CMapParser
-from cmap import FontMetricsDB, EncodingDB
+from cmapdb import FontMetricsDB, EncodingDB
 from struct import pack, unpack
 from psparser import LIT, STRICT
 from psparser import PSLiteral, literal_name
@@ -387,7 +387,7 @@ class PDFSimpleFont(PDFFont):
         if 'ToUnicode' in spec:
             strm = stream_value(spec['ToUnicode'])
             self.ucs2_cmap = CMap()
-            CMapParser(self.ucs2_cmap, StringIO(strm.get_data())).run()
+            CMapParser(None, self.ucs2_cmap, StringIO(strm.get_data())).run()
         PDFFont.__init__(self, descriptor, widths)
         return
 
@@ -494,7 +494,7 @@ class PDFCIDFont(PDFFont):
         if 'ToUnicode' in spec:
             strm = stream_value(spec['ToUnicode'])
             self.ucs2_cmap = CMap()
-            CMapParser(self.ucs2_cmap, StringIO(strm.get_data())).run()
+            CMapParser(None, self.ucs2_cmap, StringIO(strm.get_data())).run()
         elif self.cidcoding == 'Adobe-Identity':
             if ttf:
                 try:

pdfminer/pdfinterp.py

@@ -6,7 +6,7 @@ try:
     from cStringIO import StringIO
 except ImportError:
     from StringIO import StringIO
-from cmap import CMapDB
+from cmapdb import CMapDB
 from psparser import PSException, PSTypeError, PSEOF
 from psparser import PSKeyword, literal_name, keyword_name
 from psparser import PSStackParser

pdfminer/pdfparser.py

@@ -695,7 +695,7 @@ class PDFParser(PSStackParser):
 
 ##  PDFObjStrmParser
 ##
-class PDFObjStrmParser(PDFParser):
+class PDFObjStrmParser(PSStackParser):
 
     def __init__(self, doc, data):
         PDFParser.__init__(self, doc, StringIO(data))

tools/pdf2txt.py

@@ -4,7 +4,7 @@ from pdfminer.pdfparser import PDFDocument, PDFParser
 from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
 from pdfminer.pdfdevice import PDFDevice
 from pdfminer.converter import XMLConverter, HTMLConverter, TextConverter, TagExtractor
-from pdfminer.cmap import CMapDB, find_cmap_path
+from pdfminer.cmapdb import CMapDB, find_cmap_path
 from pdfminer.layout import LAParams
 
 # main