Support for marked content section IDs (#961)

tests/test_convert.py

@@ -70,7 +70,7 @@ class Test(unittest.TestCase):
         assert c.split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
             '18.0,12.996,,,,,,TimesNewRomanPSMT,,,"(1, 0, 0, 1, 45.83, 660.69)"'
-            ',DeviceRGB,"(0, 0, 0)",,,18.0,,,,,,Y,,1,'
+            ',,DeviceRGB,"(0, 0, 0)",,,18.0,,,,,,,Y,,1,'
         )
 
         io = StringIO()
@@ -125,7 +125,7 @@ class Test(unittest.TestCase):
         assert res.decode("utf-8").split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
             '18.0,12.996,,,,,,TimesNewRomanPSMT,,,"(1, 0, 0, 1, 45.83, 660.69)"'
-            ',DeviceRGB,"(0, 0, 0)",,,18.0,,,,,,Y,,1,'
+            ',,DeviceRGB,"(0, 0, 0)",,,18.0,,,,,,,Y,,1,'
         )
 
     def test_cli_csv_exclude(self):
@@ -141,6 +141,7 @@ class Test(unittest.TestCase):
                 "3",
                 "--exclude-attrs",
                 "matrix",
+                "mcid",
                 "ncs",
                 "non_stroking_pattern",
                 "stroking_pattern",
@@ -150,7 +151,7 @@ class Test(unittest.TestCase):
         assert res.decode("utf-8").split("\r\n")[9] == (
             "char,1,45.83,58.826,656.82,674.82,117.18,117.18,135.18,12.996,"
             "18.0,12.996,,,,,,TimesNewRomanPSMT,"
-            ',,"(0, 0, 0)",,18.0,,,,,Y,,1,'
+            ',,"(0, 0, 0)",,18.0,,,,,,Y,,1,'
         )
 
     def test_cli_csv_include(self):

tests/test_mcids.py

@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+
+import os
+import unittest
+
+import pdfplumber
+
+HERE = os.path.abspath(os.path.dirname(__file__))
+
+
+class TestMCIDs(unittest.TestCase):
+    """Test MCID extraction."""
+
+    def test_mcids(self):
+        path = os.path.join(HERE, "pdfs/mcid_example.pdf")
+
+        pdf = pdfplumber.open(path)
+        page = pdf.pages[0]
+        # Check text of MCIDS
+        mcids = []
+        for c in page.chars:
+            if "mcid" in c:
+                while len(mcids) <= c["mcid"]:
+                    mcids.append("")
+                if not mcids[c["mcid"]]:
+                    mcids[c["mcid"]] = c["tag"] + ": "
+                mcids[c["mcid"]] += c["text"]
+        assert mcids == [
+            "Standard: Test of figures",
+            "",
+            "P: 1 ligne",
+            "P: 2 ligne",
+            "P: 3 ligne",
+            "P: 4 ligne",
+            "P: 0",
+            "P: 2",
+            "P: 4",
+            "P: 6",
+            "P: 8",
+            "P: 10",
+            "P: 12",
+            "P: Figure 1: Chart",
+            "",
+            "P: 1 colonne",
+            "P: 2 colonne",
+            "P: 3 colonne",
+        ]
+        # Check line and curve MCIDs
+        line_mcids = set(x["mcid"] for x in page.lines)
+        curve_mcids = set(x["mcid"] for x in page.curves)
+        assert all(x["tag"] == "Figure" for x in page.lines)
+        assert all(x["tag"] == "Figure" for x in page.curves)
+        assert line_mcids & {1, 14}
+        assert curve_mcids & {1, 14}
+        # No rects to test unfortunately!