American amount to decimal conversion; PDF decompression function; regexp-based tokenizer. Part of #1641

weboob/tools/pdf.py

@@ -0,0 +1,49 @@
+# -*- coding: utf-8 -*-
+
+# Copyright(C) 2014 Oleg Plakhotniuk
+#
+# This file is part of weboob.
+#
+# weboob is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# weboob is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with weboob. If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import subprocess
+from tempfile import mkstemp
+
+
+__all__ = ['decompress_pdf']
+
+
+def decompress_pdf(inpdf):
+    """
+    Takes PDF file contents as a string and returns decompressed version
+    of the file contents, suitable for text parsing.
+
+    External dependencies:
+    MuPDF (http://www.mupdf.com).
+    """
+
+    inh, inname = mkstemp(suffix='.pdf')
+    outh, outname = mkstemp(suffix='.pdf')
+    os.write(inh, inpdf)
+    os.close(inh)
+    os.close(outh)
+
+    subprocess.call(['mutool', 'clean', '-d', inname, outname])
+
+    with open(outname) as f:
+        outpdf = f.read()
+    os.remove(inname)
+    os.remove(outname)
+    return outpdf