Add Python 3 compatibility (#109)

* Add python3 compat

* Update .gitignore

* Update .gitignore again

* Remove debugging return

* Add unicode_literals import

* Bump version

* Add python3-tk note

camelot/__version__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-VERSION = (0, 1, 2)
+VERSION = (0, 2, 0)
 
 __title__ = 'camelot-py'
 __description__ = 'PDF Table Extraction for Humans.'

camelot/parsers/lattice.py

@@ -13,7 +13,7 @@ from .base import BaseParser
 from ..core import Table
 from ..utils import (scale_image, scale_pdf, segments_in_bbox, text_in_bbox,
                      merge_close_lines, get_table_index, compute_accuracy,
-                     compute_whitespace, setup_logging, encode_)
+                     compute_whitespace, setup_logging)
 from ..image_processing import (adaptive_threshold, find_lines,
                                 find_table_contours, find_table_joints)
 
@@ -177,7 +177,7 @@ class Lattice(BaseParser):
         gs_call = [
             "-q", "-sDEVICE=png16m", "-o", self.imagename, "-r600", self.filename
         ]
-        if "ghostscript" in subprocess.check_output(["gs", "-version"]).lower():
+        if "ghostscript" in subprocess.check_output(["gs", "-version"]).decode('utf-8').lower():
             gs_call.insert(0, "gs")
         else:
             gs_call.insert(0, "gsc")
@@ -284,7 +284,6 @@ class Lattice(BaseParser):
             table = Lattice._copy_spanning_text(table, copy_text=self.copy_text)
 
         data = table.data
-        data = encode_(data)
         table.df = pd.DataFrame(data)
         table.shape = table.df.shape
 

camelot/parsers/stream.py

@@ -10,7 +10,7 @@ import pandas as pd
 from .base import BaseParser
 from ..core import Table
 from ..utils import (text_in_bbox, get_table_index, compute_accuracy,
-                     compute_whitespace, setup_logging, encode_)
+                     compute_whitespace, setup_logging)
 
 
 logger = setup_logging(__name__)
@@ -323,7 +323,6 @@ class Stream(BaseParser):
         accuracy = compute_accuracy([[100, pos_errors]])
 
         data = table.data
-        data = encode_(data)
         table.df = pd.DataFrame(data)
         table.shape = table.df.shape
 

camelot/utils.py

@@ -560,7 +560,7 @@ def get_table_index(table, t, direction, split_text=False, flag_size=False):
                     lt_col_overlap.append(abs(left - right) / abs(c[0] - c[1]))
                 else:
                     lt_col_overlap.append(-1)
-            if len(filter(lambda x: x != -1, lt_col_overlap)) == 0:
+            if len(list(filter(lambda x: x != -1, lt_col_overlap))) == 0:
                 text = t.get_text().strip('\n')
                 text_range = (t.x0, t.x1)
                 col_range = (table.cols[0][0], table.cols[-1][1])
@@ -669,22 +669,6 @@ def remove_empty(d):
     return d
 
 
-def encode_(ar):
-    """Encodes two-dimensional list into unicode.
-
-    Parameters
-    ----------
-    ar : list
-
-    Returns
-    -------
-    ar : list
-
-    """
-    ar = [[r.encode('utf-8') for r in row] for row in ar]
-    return ar
-
-
 def get_page_layout(filename, char_margin=1.0, line_margin=0.5, word_margin=0.1,
                detect_vertical=True, all_texts=True):
     """Returns a PDFMiner LTPage object and page dimension of a single
@@ -709,7 +693,7 @@ def get_page_layout(filename, char_margin=1.0, line_margin=0.5, word_margin=0.1,
         Dimension of pdf page in the form (width, height).
 
     """
-    with open(filename, 'r') as f:
+    with open(filename, 'rb') as f:
         parser = PDFParser(f)
         document = PDFDocument(parser)
         if not document.is_extractable: