Merge branch 'master' into format-markdown

camelot/__version__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-VERSION = (0, 8, 2)
+VERSION = (0, 9, 0)
 PRERELEASE = None  # alpha, beta or rc
 REVISION = None
 

camelot/core.py

@@ -55,7 +55,9 @@ class TextEdge(object):
         x = round(self.x, 2)
         y0 = round(self.y0, 2)
         y1 = round(self.y1, 2)
-        return f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
+        return (
+            f"<TextEdge x={x} y0={y0} y1={y1} align={self.align} valid={self.is_valid}>"
+        )
 
     def update_coords(self, x, y0, edge_tol=50):
         """Updates the text edge's x and bottom y coordinates and sets
@@ -102,8 +104,7 @@ class TextEdges(object):
         return None
 
     def add(self, textline, align):
-        """Adds a new text edge to the current dict.
-        """
+        """Adds a new text edge to the current dict."""
         x = self.get_x_coord(textline, align)
         y0 = textline.y0
         y1 = textline.y1
@@ -111,8 +112,7 @@ class TextEdges(object):
         self._textedges[align].append(te)
 
     def update(self, textline):
-        """Updates an existing text edge in the current dict.
-        """
+        """Updates an existing text edge in the current dict."""
         for align in ["left", "right", "middle"]:
             x_coord = self.get_x_coord(textline, align)
             idx = self.find(x_coord, align)
@@ -304,8 +304,7 @@ class Cell(object):
 
     @property
     def bound(self):
-        """The number of sides on which the cell is bounded.
-        """
+        """The number of sides on which the cell is bounded."""
         return self.top + self.bottom + self.left + self.right
 
 
@@ -361,8 +360,7 @@ class Table(object):
 
     @property
     def data(self):
-        """Returns two-dimensional list of strings in table.
-        """
+        """Returns two-dimensional list of strings in table."""
         d = []
         for row in self.cells:
             d.append([cell.text.strip() for cell in row])
@@ -383,8 +381,7 @@ class Table(object):
         return report
 
     def set_all_edges(self):
-        """Sets all table edges to True.
-        """
+        """Sets all table edges to True."""
         for row in self.cells:
             for cell in row:
                 cell.left = cell.right = cell.top = cell.bottom = True
@@ -526,8 +523,7 @@ class Table(object):
         return self
 
     def set_border(self):
-        """Sets table border edges to True.
-        """
+        """Sets table border edges to True."""
         for r in range(len(self.rows)):
             self.cells[r][0].left = True
             self.cells[r][len(self.cols) - 1].right = True

camelot/ext/ghostscript/__init__.py

@@ -81,8 +81,7 @@ class __Ghostscript(object):
 
 
 def Ghostscript(*args, **kwargs):
-    """Factory function for setting up a Ghostscript instance
-    """
+    """Factory function for setting up a Ghostscript instance"""
     global __instance__
     # Ghostscript only supports a single instance
     if __instance__ is None:

camelot/handlers.py

@@ -167,9 +167,7 @@ class PDFHandler(object):
         with TemporaryDirectory() as tempdir:
             for p in self.pages:
                 self._save_page(self.filepath, p, tempdir)
-            pages = [
-                os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages
-            ]
+            pages = [os.path.join(tempdir, f"page-{p}.pdf") for p in self.pages]
             parser = Lattice(**kwargs) if flavor == "lattice" else Stream(**kwargs)
             for p in pages:
                 t = parser.extract_tables(

camelot/parsers/base.py

@@ -6,8 +6,7 @@ from ..utils import get_page_layout, get_text_objects
 
 
 class BaseParser(object):
-    """Defines a base parser.
-    """
+    """Defines a base parser."""
 
     def _generate_layout(self, filename, layout_kwargs):
         self.filename = filename

camelot/parsers/lattice.py

@@ -211,8 +211,8 @@ class Lattice(BaseParser):
         from ..ext.ghostscript import Ghostscript
 
         self.imagename = "".join([self.rootname, ".png"])
-        gs_call = "-q -sDEVICE=png16m -o {} -r300 {}".format(
-            self.imagename, self.filename
+        gs_call = "-q -sDEVICE=png16m -o {} -r{} {}".format(
+            self.imagename, self.resolution, self.filename
         )
         gs_call = gs_call.encode().split()
         null = open(os.devnull, "wb")

camelot/parsers/stream.py

@@ -65,7 +65,7 @@ class Stream(BaseParser):
         edge_tol=50,
         row_tol=2,
         column_tol=0,
-        **kwargs
+        **kwargs,
     ):
         self.table_regions = table_regions
         self.table_areas = table_areas
@@ -362,10 +362,10 @@ class Stream(BaseParser):
                     if len(elements):
                         ncols = max(set(elements), key=elements.count)
                     else:
-                        warnings.warn(
-                            f"No tables found in table area {table_idx + 1}"
-                        )
-                cols = [(t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r]
+                        warnings.warn(f"No tables found in table area {table_idx + 1}")
+                cols = [
+                    (t.x0, t.x1) for r in rows_grouped if len(r) == ncols for t in r
+                ]
                 cols = self._merge_columns(sorted(cols), column_tol=self.column_tol)
                 inner_text = []
                 for i in range(1, len(cols)):

camelot/plotting.py

@@ -34,13 +34,9 @@ class PlotMethods(object):
             raise ImportError("matplotlib is required for plotting.")
 
         if table.flavor == "lattice" and kind in ["textedge"]:
-            raise NotImplementedError(
-                f"Lattice flavor does not support kind='{kind}'"
-            )
+            raise NotImplementedError(f"Lattice flavor does not support kind='{kind}'")
         elif table.flavor == "stream" and kind in ["joint", "line"]:
-            raise NotImplementedError(
-                f"Stream flavor does not support kind='{kind}'"
-            )
+            raise NotImplementedError(f"Stream flavor does not support kind='{kind}'")
 
         plot_method = getattr(self, kind)
         fig = plot_method(table)
@@ -48,7 +44,7 @@ class PlotMethods(object):
         if filename is not None:
             fig.savefig(filename)
             return None
-            
+
         return fig
 
     def text(self, table):

camelot/utils.py

@@ -838,23 +838,27 @@ def compute_whitespace(d):
 
 def get_page_layout(
     filename,
+    line_overlap=0.5,
     char_margin=1.0,
     line_margin=0.5,
     word_margin=0.1,
+    boxes_flow=0.5,
     detect_vertical=True,
     all_texts=True,
 ):
     """Returns a PDFMiner LTPage object and page dimension of a single
-    page pdf. See https://euske.github.io/pdfminer/ to get definitions
-    of kwargs.
+    page pdf. To get the definitions of kwargs, see
+    https://pdfminersix.rtfd.io/en/latest/reference/composable.html.
 
     Parameters
     ----------
     filename : string
         Path to pdf file.
+    line_overlap : float
     char_margin : float
     line_margin : float
     word_margin : float
+    boxes_flow : float
     detect_vertical : bool
     all_texts : bool
 
@@ -870,11 +874,15 @@ def get_page_layout(
         parser = PDFParser(f)
         document = PDFDocument(parser)
         if not document.is_extractable:
-            raise PDFTextExtractionNotAllowed(f"Text extraction is not allowed: {filename}")
+            raise PDFTextExtractionNotAllowed(
+                f"Text extraction is not allowed: {filename}"
+            )
         laparams = LAParams(
+            line_overlap=line_overlap,
             char_margin=char_margin,
             line_margin=line_margin,
             word_margin=word_margin,
+            boxes_flow=boxes_flow,
             detect_vertical=detect_vertical,
             all_texts=all_texts,
         )