More linting, refactor

camelot/handlers.py

@@ -25,7 +25,7 @@ PARSERS = {
 }
 
 
-class PDFHandler(object):
+class PDFHandler():
     """Handles all operations like temp directory creation, splitting
     file into single page PDFs, parsing each PDF and then removing the
     temp directory.
@@ -201,8 +201,8 @@ class PDFHandler(object):
                 page_idx,
                 layout_kwargs=layout_kwargs
             )
-            parser._generate_layout(source_file, layout, dimensions,
-                                    page_idx, layout_kwargs)
+            parser.prepare_page_parse(source_file, layout, dimensions,
+                                      page_idx, layout_kwargs)
             rootname = os.path.basename(parser.rootname)
             if not suppress_stdout:
                 logger.info(

camelot/parsers/base.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 
 import os
+import warnings
 
 from ..utils import (
     get_text_objects,
@@ -40,8 +41,8 @@ class BaseParser(object):
         # For plotting details of parsing algorithms
         self.debug_info = {}
 
-    def _generate_layout(self, filename, layout, dimensions,
-                         page_idx, layout_kwargs):
+    def prepare_page_parse(self, filename, layout, dimensions,
+                           page_idx, layout_kwargs):
         self.filename = filename
         self.layout_kwargs = layout_kwargs
         self.layout = layout
@@ -59,6 +60,22 @@ class BaseParser(object):
         self.pdf_width, self.pdf_height = self.dimensions
         self.rootname, __ = os.path.splitext(self.filename)
 
+    def _document_has_no_text(self):
+        if not self.horizontal_text:
+            rootname = os.path.basename(self.rootname)
+            if self.images:
+                warnings.warn(
+                    "{rootname} is image-based, "
+                    "camelot only works on text-based pages."
+                    .format(rootname=rootname)
+                )
+            else:
+                warnings.warn(
+                    "No tables found on {rootname}".format(rootname=rootname)
+                )
+            return True
+        return False
+
     """Initialize new table object, ready to be populated
 
     Parameters

camelot/parsers/lattice.py

@@ -3,7 +3,6 @@
 from __future__ import division
 import os
 import copy
-import warnings
 
 
 from .base import BaseParser
@@ -312,18 +311,7 @@ class Lattice(BaseParser):
         return table
 
     def extract_tables(self, filename):
-        rootname = os.path.basename(self.rootname)
-        if not self.horizontal_text:
-            if self.images:
-                warnings.warn(
-                    "{rootname} is image-based, "
-                    "camelot only works on text-based pages."
-                    .format(rootname=rootname)
-                )
-            else:
-                warnings.warn(
-                    "No tables found on {rootname}".format(rootname=rootname)
-                )
+        if self._document_has_no_text():
             return []
 
         self._generate_table_bbox()

camelot/parsers/stream.py

@@ -1,7 +1,6 @@
 # -*- coding: utf-8 -*-
 
 from __future__ import division
-import os
 import warnings
 
 import numpy as np
@@ -427,18 +426,7 @@ class Stream(BaseParser):
         return table
 
     def extract_tables(self, filename):
-        if not self.horizontal_text:
-            if self.images:
-                warnings.warn(
-                    "{} is image-based, camelot only works on"
-                    " text-based pages.".format(
-                        os.path.basename(self.rootname))
-                )
-            else:
-                warnings.warn(
-                    "No tables found on {}".format(
-                        os.path.basename(self.rootname))
-                )
+        if self._document_has_no_text():
             return []
 
         # Identify plausible areas within the doc where tables lie,

camelot/utils.py

@@ -1107,11 +1107,15 @@ def compare_tables(left, right):
                     diff_df = diff_df.append(lrow, ignore_index=True)
                     diff_df = diff_df.append(srow, ignore_index=True)
                     diff_df.insert(0, 'Table', [name_table1, name_table2])
-                    print(f"Row {index} differs:")
+                    print("Row {index} differs:".format(index=index))
                     print(diff_df.values)
                     break
             else:
-                print(f"Row {index} unique to {name_table1}: {lrow}")
+                print("Row {index} unique to {name_table1}: {lrow}".format(
+                    index=index,
+                    name_table1=name_table1,
+                    lrow=lrow
+                ))
                 break
     else:
         print("Tables have different shapes")