Add resolution

camelot/cli.py

@@ -84,6 +84,8 @@ def cli(ctx, *args, **kwargs):
               ' may be zero or negative as well.')
 @click.option('-I', '--iterations', default=0,
               help='Number of times for erosion/dilation will be applied.')
+@click.option('-res', '--resolution', default=300,
+              help='Resolution used for PDF to PNG conversion.')
 @click.option('-plot', '--plot_type',
               type=click.Choice(['text', 'grid', 'contour', 'joint', 'line']),
               help='Plot elements found on PDF page for visual debugging.')

camelot/core.py

@@ -72,7 +72,8 @@ class TextEdges(object):
     the PDF page. The dict has three keys based on the alignments,
     and each key's value is a list of camelot.core.TextEdge objects.
     """
-    def __init__(self):
+    def __init__(self, edge_close_tol=50):
+        self.edge_close_tol = edge_close_tol
         self._textedges = {'left': [], 'right': [], 'middle': []}
 
     @staticmethod
@@ -104,7 +105,7 @@ class TextEdges(object):
         te = TextEdge(x, y0, y1, align=align)
         self._textedges[align].append(te)
 
-    def update(self, textline, edge_close_tol=50):
+    def update(self, textline):
         """Updates an existing text edge in the current dict.
         """
         for align in ['left', 'right', 'middle']:
@@ -114,15 +115,15 @@ class TextEdges(object):
                 self.add(textline, align)
             else:
                 self._textedges[align][idx].update_coords(
-                    x_coord, textline.y0, edge_close_tol=edge_close_tol)
+                    x_coord, textline.y0, edge_close_tol=self.edge_close_tol)
 
-    def generate(self, textlines, edge_close_tol=50):
+    def generate(self, textlines):
         """Generates the text edges dict based on horizontal text
         rows.
         """
         for tl in textlines:
             if len(tl.get_text().strip()) > 1: # TODO: hacky
-                self.update(tl, edge_close_tol=edge_close_tol)
+                self.update(tl)
 
     def get_relevant(self):
         """Returns the list of relevant text edges (all share the same

camelot/parsers/lattice.py

@@ -76,7 +76,7 @@ class Lattice(BaseParser):
                  line_size_scaling=15, copy_text=None, shift_text=['l', 't'],
                  split_text=False, flag_size=False, line_close_tol=2,
                  joint_close_tol=2, threshold_blocksize=15, threshold_constant=-2,
-                 iterations=0, **kwargs):
+                 iterations=0, resolution=300, **kwargs):
         self.table_areas = table_areas
         self.process_background = process_background
         self.line_size_scaling = line_size_scaling
@@ -89,6 +89,7 @@ class Lattice(BaseParser):
         self.threshold_blocksize = threshold_blocksize
         self.threshold_constant = threshold_constant
         self.iterations = iterations
+        self.resolution = resolution
 
     @staticmethod
     def _reduce_index(t, idx, shift_text):
@@ -209,7 +210,7 @@ class Lattice(BaseParser):
             '-sDEVICE=png16m',
             '-o',
             self.imagename,
-            '-r600',
+            '-r{}'.format(self.resolution),
             self.filename
         ]
         gs = get_executable()

camelot/parsers/stream.py

@@ -255,9 +255,9 @@ class Stream(BaseParser):
         # TODO: add support for arabic text #141
         # sort textlines in reading order
         textlines.sort(key=lambda x: (-x.y0, x.x0))
-        textedges = TextEdges()
+        textedges = TextEdges(edge_close_tol=self.edge_close_tol)
         # generate left, middle and right textedges
-        textedges.generate(textlines, edge_close_tol=self.edge_close_tol)
+        textedges.generate(textlines)
         # select relevant edges
         relevant_textedges = textedges.get_relevant()
         self.textedges.extend(relevant_textedges)