From 5e2206bae76fe4b98f353676fdb37d8092a305e4 Mon Sep 17 00:00:00 2001
From: Dima Kuznetsov <dmitrykuzn@gmail.com>
Date: Sat, 20 Feb 2021 02:55:35 +0200
Subject: [PATCH] Allow --sidecar along --pages (#735)

---
 src/ocrmypdf/_pipeline.py   | 26 +++++++++--
 src/ocrmypdf/_validation.py |  2 -
 tests/test_pipeline.py      | 87 +++++++++++++++++++++++++++++++++++++
 tests/test_validation.py    |  2 -
 4 files changed, 110 insertions(+), 7 deletions(-)

diff --git a/src/ocrmypdf/_pipeline.py b/src/ocrmypdf/_pipeline.py
index 28ddf6e2..3ca5e97f 100644
--- a/src/ocrmypdf/_pipeline.py
+++ b/src/ocrmypdf/_pipeline.py
@@ -808,11 +808,27 @@ def optimize_pdf(input_file: Path, context: PdfContext):
     return output_file
 
 
+def enumerate_compress_ranges(iterable):
+    skipped_from = None
+    for index, txt_file in enumerate(iterable):
+        index += 1
+        if txt_file:
+            if skipped_from is not None:
+                yield (skipped_from, index - 1), None
+                skipped_from = None
+            yield (index, index), txt_file
+        else:
+            if skipped_from is None:
+                skipped_from = index
+    if skipped_from is not None:
+        yield (skipped_from, index), None
+
+
 def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
-        for page_num, txt_file in enumerate(txt_files):
-            if page_num != 0:
+        for (frm, to), txt_file in enumerate_compress_ranges(txt_files):
+            if frm != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
                 with open(txt_file, 'r', encoding="utf-8") as in_:
@@ -825,7 +841,11 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
                     else:
                         stream.write(txt)
             else:
-                stream.write(f'[OCR skipped on page {(page_num + 1)}]')
+                if frm != to:
+                    pages = f'{frm}-{to}'
+                else:
+                    pages = f'{frm}'
+                stream.write(f'[OCR skipped on page(s) {pages}]')
     return output_file
 
 
diff --git a/src/ocrmypdf/_validation.py b/src/ocrmypdf/_validation.py
index a6ee9a08..2e2cd529 100644
--- a/src/ocrmypdf/_validation.py
+++ b/src/ocrmypdf/_validation.py
@@ -184,8 +184,6 @@ def check_options_ocr_behavior(options):
     )
     if exclusive_options >= 2:
         raise BadArgsError("Choose only one of --force-ocr, --skip-text, --redo-ocr.")
-    if options.pages and options.sidecar:
-        raise BadArgsError("--pages and --sidecar are mutually exclusive")
     if options.pages:
         options.pages = _pages_from_ranges(options.pages)
 
diff --git a/tests/test_pipeline.py b/tests/test_pipeline.py
index 64254e84..becef2c4 100644
--- a/tests/test_pipeline.py
+++ b/tests/test_pipeline.py
@@ -61,3 +61,90 @@ def test_dpi_needed(image, text, vector, result, rgb_image, outdir):
 
     assert _pipeline.get_canvas_square_dpi(pi[0], mock) == result
     assert _pipeline.get_page_square_dpi(pi[0], mock) == result
+
+
+@pytest.mark.parametrize(
+    # Name for nicer -v output
+    'name,input,output',
+    (
+        (
+            'empty_input',
+            # Input:
+            (),
+            # Output:
+            (),
+        ),
+        (
+            'no_values',
+            # Input:
+            ('', '', '', '', ''),
+            # Output:
+            (
+                ((1, 5), None),
+            ),
+        ),
+        (
+            'no_empty_values',
+            # Input:
+            ('v', 'w', 'x', 'y', 'z'),
+            # Output:
+            (
+                ((1, 1), 'v'),
+                ((2, 2), 'w'),
+                ((3, 3), 'x'),
+                ((4, 4), 'y'),
+                ((5, 5), 'z'),
+            ),
+        ),
+        (
+            'skip_head',
+            # Input:
+            ('', '', 'x', 'y', 'z'),
+            # Output:
+            (
+                ((1, 2), None),
+                ((3, 3), 'x'),
+                ((4, 4), 'y'),
+                ((5, 5), 'z'),
+            ),
+        ),
+        (
+            'skip_tail',
+            # Input:
+            ('x', 'y', 'z', '', ''),
+            # Output:
+            (
+                ((1, 1), 'x'),
+                ((2, 2), 'y'),
+                ((3, 3), 'z'),
+                ((4, 5), None),
+            ),
+        ),
+        (
+            'range_in_middle',
+            # Input:
+            ('x', '', '', '', 'y'),
+            # Output:
+            (
+                ((1, 1), 'x'),
+                ((2, 4), None),
+                ((5, 5), 'y'),
+            ),
+        ),
+        (
+            'range_in_middle_2',
+            # Input:
+            ('x', '', '', 'y', '', '', '', 'z'),
+            # Output:
+            (
+                ((1, 1), 'x'),
+                ((2, 3), None),
+                ((4, 4), 'y'),
+                ((5, 7), None),
+                ((8, 8), 'z'),
+            ),
+        ),
+    ),
+)
+def test_enumerate_compress_ranges(name, input, output):
+    assert output == tuple(_pipeline.enumerate_compress_ranges(input))
\ No newline at end of file
diff --git a/tests/test_validation.py b/tests/test_validation.py
index f7ce5286..6eb53e48 100644
--- a/tests/test_validation.py
+++ b/tests/test_validation.py
@@ -90,8 +90,6 @@ def test_mutex_options():
         vd.check_options_ocr_behavior(make_opts(redo_ocr=True, skip_text=True))
     with pytest.raises(BadArgsError):
         vd.check_options_ocr_behavior(make_opts(redo_ocr=True, force_ocr=True))
-    with pytest.raises(BadArgsError):
-        vd.check_options_ocr_behavior(make_opts(pages='1-3', sidecar='file.txt'))
 
 
 def test_optimizing(caplog):