fix pychecker warning

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@104 1aa58f4a-7d42-0410-adbc-911cccaed67c

Makefile

@@ -1,12 +1,12 @@
 # Makefile for pdfminer
 
 PACKAGE=pdfminer
-VERSION=20090330
-GNUTAR=tar
-SVN=svn
-PYTHON=python
 
-WORKDIR=/tmp
+SVN=svn
+GNUTAR=tar
+PYTHON=python
+TMPDIR=/tmp
+VERSION=`$(PYTHON) $(PACKAGE)/__init__.py`
 DISTNAME=$(PACKAGE)-dist-$(VERSION)
 DISTFILE=$(DISTNAME).tar.gz
 
@@ -14,34 +14,33 @@ CONV_CMAP=$(PYTHON) -m tools.conv_cmap
 
 all:
 
+clean:
+	-rm -rf build
+	-cd $(PACKAGE) && make clean
+	-cd tools && make clean
+	-cd samples && make clean
+
+test:
+	cd samples && make test
+
 cdbcmap: CMap
 	-mkdir CDBCMap
 	$(CONV_CMAP) CMap/*
 
-test:
-	cd samples && make
-
-clean:
-	-cd pdflib && make clean
-	-cd tools && make clean
-	-cd samples && make clean
-	-rm -rf build
-
 # Maintainance:
-
-pack: clean
-	$(SVN) cleanup
-	$(SVN) export . $(WORKDIR)/$(DISTNAME)
-	$(GNUTAR) c -z -C$(WORKDIR) -f $(WORKDIR)/$(DISTFILE) $(DISTNAME) --dereference --numeric-owner
-	-rm -rf $(WORKDIR)/$(DISTNAME)
-
-check:
-	-pychecker --limit=0 *.py
-
 commit: clean
 	$(SVN) commit
 
+check:
+	cd $(PACKAGE) && make check
+
+dist: clean
+	$(SVN) cleanup
+	$(SVN) export . $(TMPDIR)/$(DISTNAME)
+	$(GNUTAR) c -z -C$(TMPDIR) -f $(TMPDIR)/$(DISTFILE) $(DISTNAME) --dereference --numeric-owner
+	-rm -rf $(TMPDIR)/$(DISTNAME)
+
 WEBDIR=$$HOME/Site/unixuser.org/python/pdfminer
-publish: pack
+publish: dist
-	cp $(WORKDIR)/$(DISTFILE) $(WEBDIR)
+	cp $(TMPDIR)/$(DISTFILE) $(WEBDIR)
 	cp README.html $(WEBDIR)/index.html

pdfminer/Makefile

@@ -1,32 +1,11 @@
 # Makefile for pdfminer
 
-DESTDIR=/usr/local/src/pdflib
+PYCHECKER=pychecker --limit=0
 
-PDFLIB = ${DESTDIR}/__init__.py \
+all:
-	${DESTDIR}/arcfour.py \
-	${DESTDIR}/ascii85.py \
-	${DESTDIR}/cmap.py \
-	${DESTDIR}/fontmetrics.py \
-	${DESTDIR}/glyphlist.py \
-	${DESTDIR}/latin_enc.py \
-	${DESTDIR}/lzw.py \
-	${DESTDIR}/pdf2txt.py \
-	${DESTDIR}/pdfcolor.py \
-	${DESTDIR}/pdfdevice.py \
-	${DESTDIR}/pdffont.py \
-	${DESTDIR}/pdfinterp.py \
-	${DESTDIR}/pdfparser.py \
-	${DESTDIR}/pdftypes.py \
-	${DESTDIR}/psparser.py \
-	${DESTDIR}/pycdb.py \
-	${DESTDIR}/rijndael.py \
-	${DESTDIR}/utils.py \
-
-${DESTDIR}/%: %
-	cp $? $@
-	chmod 755 $@
-
-all: ${PDFLIB}
 
 clean:
 	-rm *.pyc *.pyo
+
+check:
+	$(PYCHECKER) *.py

pdfminer/__init__.py

@@ -0,0 +1,4 @@
+#!/usr/bin/env python
+__version__ = '20090330'
+
+if __name__ == '__main__': print __version__

pdfminer/converter.py

@@ -45,7 +45,7 @@ class PDFPageAggregator(PDFDevice):
 
   def handle_undefined_char(self, cidcoding, cid):
     if self.debug:
-      print >>stderr, 'undefined: %r, %r' % (cidcoding, cid)
+      print >>sys.stderr, 'undefined: %r, %r' % (cidcoding, cid)
     return self.undefined_char
 
   def paint_path(self, gstate, stroke, fill, evenodd, path):
@@ -149,7 +149,7 @@ class TagExtractor(PDFDevice):
           text += char
         except PDFUnicodeNotDefined:
           pass
-    self.write(text)
+    self.outfp.write(enc(text, self.codec))
     return
 
   def begin_page(self, page):
@@ -306,18 +306,17 @@ class TextConverter(PDFConverter):
   def end_page(self, page):
     def render(item):
       if isinstance(item, LTText):
-        self.outfp.write(obj.text.encode(self.codec, 'replace'))
+        self.write(item.text+'\n')
-        self.outfp.write('\n')
       elif isinstance(item, LTTextBox):
         for line in item.get_lines(self.word_margin):
-          self.outfp.write(line.encode(self.codec, 'replace')+'\n')
+          self.write(line+'\n')
-        self.outfp.write('\n')
+        self.write('\n')
       elif isinstance(item, LayoutContainer):
         for child in item:
           render(child)
     page = PDFConverter.end_page(self, page)
     if self.showpageno:
-      self.outfp.write('Page %d\n' % page.id)
+      self.write('Page %d\n' % page.id)
     render(page)
-    self.outfp.write('\f')
+    self.write('\f')
     return

pdfminer/layout.py

@@ -362,7 +362,7 @@ class LTFigure(LayoutContainer):
     return
 
   def __repr__(self):
-    return ('<figure id=%r bbox=%s ctm=%r>' % (self.id, self.get_bbox(), self.ctm))
+    return ('<figure id=%r bbox=%s matrix=%r>' % (self.id, self.get_bbox(), self.matrix))
 
 
 ##  LTTextBox

pdfminer/lzw.py

@@ -86,12 +86,12 @@ class LZWDecoder(object):
 
 def main(argv):
   import StringIO
-  input = '\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'
+  data = '\x80\x0b\x60\x50\x22\x0c\x0c\x85\x01'
-  fp = StringIO.StringIO(input)
+  fp = StringIO.StringIO(data)
   expected = '\x2d\x2d\x2d\x2d\x2d\x41\x2d\x2d\x2d\x42'
   LZWDecoder.debug = 1
   output = ''.join(LZWDecoder(fp).run())
-  print (input, expected, output)
+  print (data, expected, output)
   print output == expected
   return 0
 

pdfminer/pdffont.py

@@ -243,7 +243,7 @@ class TrueTypeFont(object):
     self.tables = {}
     fonttype = fp.read(4)
     (ntables, _1, _2, _3) = unpack('>HHHH', fp.read(8))
-    for i in xrange(ntables):
+    for _ in xrange(ntables):
       (name, tsum, offset, length) = unpack('>4sLLL', fp.read(16))
       self.tables[name] = (offset, length)
     return

pdfminer/pdfinterp.py

@@ -152,7 +152,7 @@ class PDFResourceManager(object):
       else:
         if STRICT:
           raise PDFFontError('Invalid Font spec: %r' % spec)
-        font = PDFType1Font(spec) # this is so wrong!
+        font = PDFType1Font(self, spec) # this is so wrong!
       if objid:
         self.fonts[objid] = font
     return font

pdfminer/pdfparser.py

@@ -55,7 +55,6 @@ class XRefObjRange(object):
 class PDFBaseXRef(object):
   def __init__(self):
     self.objid_ranges = None
-    self.objid_list = None
     return
 
   def objids(self):
@@ -63,11 +62,9 @@ class PDFBaseXRef(object):
       for objid_range in self.objid_ranges:
         for objid in xrange(objid_range.get_start_id(), objid_range.get_end_id() + 1):
           yield objid
-    else:
-      for objid in self.offsets:
-        yield objid
     return
 
+
 ##  PDFXRef
 ##
 class PDFXRef(PDFBaseXRef):
@@ -154,7 +151,7 @@ class PDFXRefStream(PDFBaseXRef):
     return
 
   def __repr__(self):
-    return '<PDFXRef: objid=%d-%d>' % (self.objid_first, self.objid_last)
+    return '<PDFXRefStream: fields=%d,%d,%d>' % (self.fl1, self.fl2, self.fl3)
 
   def load(self, parser, debug=0):
     (_,objid) = parser.nexttoken() # ignored

samples/Makefile

@@ -16,11 +16,13 @@ HTMLS= \
 	naacl06-shinyama.html \
 	nlp2004slides.html
 
-all: $(HTMLS)
+all:
 
 clean:
 	-rm $(HTMLS)
 
+test: $(HTMLS)
+
 .SUFFIXES: .pdf .html .sgml .txt
 .pdf.html:
 	$(PDF2TXT) -t html -o $@ $<