From 4bdb3ba8cc79259336f797d00d9a48e93c53bdba Mon Sep 17 00:00:00 2001 From: Martin Wolf Date: Thu, 12 Apr 2018 00:05:38 +0200 Subject: [PATCH] Fixes needed to be able to compile pdfminer.six with Cython --- pdfminer/ccitt.py | 4 +++- pdfminer/cmapdb.py | 2 +- setup.py | 2 +- tools/pdf2html.cgi | 4 ++-- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/pdfminer/ccitt.py b/pdfminer/ccitt.py index efc3482..111dff6 100644 --- a/pdfminer/ccitt.py +++ b/pdfminer/ccitt.py @@ -15,6 +15,8 @@ import array import six #Python 2+3 compatibility +import unittest + if six.PY3: def get_bytes(data): for byte in data: @@ -598,7 +600,7 @@ def main(argv): pygame.image.save(self.img, 'out.bmp') return for path in argv[1:]: - fp = file(path, 'rb') + fp = open(path, 'rb') (_, _, k, w, h, _) = path.split('.') parser = Parser(int(w)) parser.feedbytes(fp.read()) diff --git a/pdfminer/cmapdb.py b/pdfminer/cmapdb.py index 4b50812..c3403d1 100644 --- a/pdfminer/cmapdb.py +++ b/pdfminer/cmapdb.py @@ -426,7 +426,7 @@ class CMapParser(PSStackParser): def main(argv): args = argv[1:] for fname in args: - fp = file(fname, 'rb') + fp = open(fname, 'rb') cmap = FileUnicodeMap() #cmap = FileCMap() CMapParser(cmap, fp).run() diff --git a/setup.py b/setup.py index 8eab391..e2a58de 100644 --- a/setup.py +++ b/setup.py @@ -3,7 +3,7 @@ import sys import pdfminer as package -requires = ['six', 'pycryptodome'] +requires = ['six', 'pycryptodome', 'pygame'] if sys.version_info >= (3, 0): requires.append('chardet') diff --git a/tools/pdf2html.cgi b/tools/pdf2html.cgi index b0f93a5..8522a04 100755 --- a/tools/pdf2html.cgi +++ b/tools/pdf2html.cgi @@ -48,7 +48,7 @@ def convert(infp, outfp, path, codec='utf-8', maxpages=0, maxfilesize=0, pagenos=None, html=True): # save the input file. - src = file(path, 'wb') + src = open(path, 'wb') nbytes = 0 while 1: data = infp.read(4096) @@ -68,7 +68,7 @@ def convert(infp, outfp, path, codec='utf-8', layoutmode='exact') else: device = TextConverter(rsrcmgr, outfp, codec=codec, laparams=laparams) - fp = file(path, 'rb') + fp = open(path, 'rb') interpreter = PDFPageInterpreter(rsrcmgr, device) for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages): interpreter.process_page(page)