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
@@ -100,6 +103,12 @@ def paint_path(self, gstate, stroke, fill, evenodd, path):
                                          stroke, fill, evenodd, gstate.scolor,
                                          gstate.ncolor))
                 return
+        if self.RECTS.match(shape):
+            for path_group in zip(*(iter(path),) * 5):
+                self.paint_path(gstate, stroke, fill, evenodd,
+                                list(path_group))
+            return
+
         # other shapes
         pts = []
         for p in path:

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', 136, 73.28), ('l', 137.28, 73.28)]
+        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', 136, 73.28), ('l', 137.28, 73.28), ('l', 137.28, 91.04), ('l', 136, 91.04), ('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', 136, 73.28), ('l', 137.28, 73.28), ('l', 137.28, 91.04), ('l', 136, 91.04), ('h',),
+            ('m', 204.8, 73.28), ('l', 206.08, 73.28), ('l', 206.08, 91.04), ('l', 204.8, 91.04), ('h',),
+            ('m', 67.2, 72), ('l', 68.48, 72), ('l', 68.48, 133.28), ('l', 67.2, 133.28), ('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: