Fix converting path to multiple rectangles

CHANGELOG.md

@@ -5,6 +5,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+### Added
+- Support for painting multiple rectangles at once ([#371](https://github.com/pdfminer/pdfminer.six/pull/371))
+
 ### Fixed
 - Validate image object in do_EI is a PDFStream ([#451](https://github.com/pdfminer/pdfminer.six/pull/451))
 

pdfminer/converter.py

@@ -27,6 +27,9 @@
 
 
 class PDFLayoutAnalyzer(PDFTextDevice):
+
+    RECTS = re.compile('^(mlllh)+$')
+
     def __init__(self, rsrcmgr, pageno=1, laparams=None):
         PDFTextDevice.__init__(self, rsrcmgr)
         self.pageno = pageno
@@ -72,6 +75,7 @@ def render_image(self, name, stream):
         return
 
     def paint_path(self, gstate, stroke, fill, evenodd, path):
+        """Paint paths described in section 4.4 of the PDF reference manual"""
         shape = ''.join(x[0] for x in path)
         if shape == 'ml':
             # horizontal/vertical line
@@ -80,11 +84,11 @@ def paint_path(self, gstate, stroke, fill, evenodd, path):
             (x0, y0) = apply_matrix_pt(self.ctm, (x0, y0))
             (x1, y1) = apply_matrix_pt(self.ctm, (x1, y1))
             if x0 == x1 or y0 == y1:
-                self.cur_item.add(LTLine(gstate.linewidth, (x0, y0), (x1, y1),
-                                         stroke, fill, evenodd, gstate.scolor,
-                                         gstate.ncolor))
-                return
-        if shape == 'mlllh':
+                line = LTLine(gstate.linewidth, (x0, y0), (x1, y1), stroke,
+                              fill, evenodd, gstate.scolor, gstate.ncolor)
+                self.cur_item.add(line)
+
+        elif shape == 'mlllh':
             # rectangle
             (_, x0, y0) = path[0]
             (_, x1, y1) = path[1]
@@ -96,18 +100,22 @@ def paint_path(self, gstate, stroke, fill, evenodd, path):
             (x3, y3) = apply_matrix_pt(self.ctm, (x3, y3))
             if (x0 == x1 and y1 == y2 and x2 == x3 and y3 == y0) or \
                     (y0 == y1 and x1 == x2 and y2 == y3 and x3 == x0):
-                self.cur_item.add(LTRect(gstate.linewidth, (x0, y0, x2, y2),
-                                         stroke, fill, evenodd, gstate.scolor,
-                                         gstate.ncolor))
-                return
-        # other shapes
-        pts = []
-        for p in path:
-            for i in range(1, len(p), 2):
-                pts.append(apply_matrix_pt(self.ctm, (p[i], p[i+1])))
-        self.cur_item.add(LTCurve(gstate.linewidth, pts, stroke, fill, evenodd,
-                                  gstate.scolor, gstate.ncolor))
-        return
+                rect = LTRect(gstate.linewidth, (x0, y0, x2, y2), stroke,
+                              fill, evenodd, gstate.scolor, gstate.ncolor)
+                self.cur_item.add(rect)
+
+        elif self.RECTS.match(shape):
+            for paths in zip(*(iter(path),) * 5):
+                self.paint_path(gstate, stroke, fill, evenodd, list(paths))
+
+        else:
+            pts = []
+            for p in path:
+                for i in range(1, len(p), 2):
+                    pts.append(apply_matrix_pt(self.ctm, (p[i], p[i+1])))
+            curve = LTCurve(gstate.linewidth, pts, stroke, fill, evenodd,
+                            gstate.scolor, gstate.ncolor)
+            self.cur_item.add(curve)
 
     def render_char(self, matrix, font, fontsize, scaling, rise, cid, ncs,
                     graphicstate):

tests/test_converter.py

@@ -0,0 +1,38 @@
+from nose.tools import assert_equal
+
+from pdfminer.converter import PDFLayoutAnalyzer
+from pdfminer.layout import LTContainer
+from pdfminer.pdfinterp import PDFGraphicState
+
+
+class TestPaintPath():
+    def test_paint_path(self):
+        path = [('m', 6, 7), ('l', 7, 7)]
+        analyzer = self._get_analyzer()
+        analyzer.cur_item = LTContainer([0, 100, 0, 100])
+        analyzer.paint_path(PDFGraphicState(), False, False, False, path)
+        assert_equal(len(analyzer.cur_item._objs), 1)
+
+    def test_paint_path_mlllh(self):
+        path = [('m', 6, 7), ('l', 7, 7), ('l', 7, 91),  ('l', 6, 91), ('h',)]
+        analyzer = self._get_analyzer()
+        analyzer.cur_item = LTContainer([0, 100, 0, 100])
+        analyzer.paint_path(PDFGraphicState(), False, False, False, path)
+        assert_equal(len(analyzer.cur_item), 1)
+
+    def test_paint_path_multiple_mlllh(self):
+        """Path from samples/contrib/issue-00369-excel.pdf"""
+        path = [
+            ('m', 6, 7), ('l', 7, 7), ('l', 7, 91), ('l', 6, 91), ('h',),
+            ('m', 4, 7), ('l', 6, 7), ('l', 6, 91), ('l', 4, 91), ('h',),
+            ('m', 67, 2), ('l', 68, 2), ('l', 68, 3), ('l', 67, 3), ('h',)
+        ]
+        analyzer = self._get_analyzer()
+        analyzer.cur_item = LTContainer([0, 100, 0, 100])
+        analyzer.paint_path(PDFGraphicState(), False, False, False, path)
+        assert_equal(len(analyzer.cur_item._objs), 3)
+
+    def _get_analyzer(self):
+        analyzer = PDFLayoutAnalyzer(None)
+        analyzer.set_ctm([1, 0, 0, 1, 0, 0])
+        return analyzer

tests/test_tools_pdf2txt.py

@@ -66,7 +66,7 @@ def test_contrib_issue_350(self):
         run('contrib/issue-00352-asw-oct96-p41.pdf')
 
     def test_scancode_patchelf(self):
-        """Regression test for # https://github.com/euske/pdfminer/issues/96"""
+        """Regression test for https://github.com/euske/pdfminer/issues/96"""
         run('scancode/patchelf.pdf')
 
     def test_contrib_hash_two_complement(self):
@@ -76,6 +76,12 @@ def test_contrib_hash_two_complement(self):
         """
         run('contrib/issue-00352-hash-twos-complement.pdf')
 
+    def test_contrib_excel(self):
+        """Regression test for
+         https://github.com/pdfminer/pdfminer.six/issues/369
+         """
+        run('contrib/issue-00369-excel.pdf', '-t html')
+
 
 class TestDumpImages: