fix: skip empty files for for not failing report generation and unnecessary actions.

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2021-2025 Codeplag Development Team
+Copyright (c) 2021-2026 Codeplag Development Team
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

docker/ubuntu2404.dockerfile

@@ -8,6 +8,7 @@ ARG DEB_PKG_NAME
 ADD LICENSE /usr/src/$UTIL_NAME/LICENSE
 ADD $DEBIAN_PACKAGES_PATH /usr/src/$UTIL_NAME/$DEBIAN_PACKAGES_PATH
 
+RUN apt-get update
 RUN apt-get install -y /usr/src/$UTIL_NAME/$DEBIAN_PACKAGES_PATH/$DEB_PKG_NAME.deb
 # TODO: Fix this hook. apt-get don't install manpage into image.
 RUN install -D -m 0644 $DEBIAN_PACKAGES_PATH/$UTIL_NAME.1 /usr/share/man/man1/

locales/codeplag.pot

@@ -1,12 +1,12 @@
 # Translations template for codeplag.
-# Copyright (C) 2024-2025 Codeplag Development Team
+# Copyright (C) 2024-2026 Codeplag Development Team
 # This file is distributed under the same license as the codeplag project.
 #
 #, fuzzy
 msgid ""
 msgstr ""
-"Project-Id-Version: codeplag 0.6.1\n"
-"POT-Creation-Date: 2025-12-02 18:35+0300\n"
+"Project-Id-Version: codeplag 0.6.2\n"
+"POT-Creation-Date: 2026-03-23 19:20+0300\n"
 "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
 "Last-Translator: Artyom Semidolin\n"
 "Language-Team: LANGUAGE <LL@li.org>\n"
@@ -242,20 +242,20 @@ msgid "There is nothing to modify; please provide at least one argument."
 msgstr ""
 
 #: src/codeplag/codeplagcli.py:443
-msgid "The'repo-regexp' option requires the provided 'github-user' option."
+msgid "The 'repo-regexp' option requires the provided 'github-user' option."
 msgstr ""
 
 #: src/codeplag/codeplagcli.py:450
 msgid ""
-"The'path-regexp' option requires the provided 'directories', 'github-"
+"The 'path-regexp' option requires the provided 'directories', 'github-"
 "user', or 'github-urls' options."
 msgstr ""
 
-#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:440
+#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:444
 msgid "All paths must be provided."
 msgstr ""
 
-#: src/codeplag/handlers/report.py:437
+#: src/codeplag/handlers/report.py:441
 msgid "Invalid report type."
 msgstr ""
 

locales/i18n.mk

@@ -23,7 +23,7 @@ translate-extract:
 		--copyright-holder "Codeplag Development Team" \
 		--last-translator "Artyom Semidolin" \
 		--output-file ${LOCALES_DIR}/${UTIL_NAME}.pot .
-	sed -ri '2 s/[0-9]{4}/2024-2025/' ${LOCALES_DIR}/${UTIL_NAME}.pot
+	sed -ri '2 s/[0-9]{4}/2024-2026/' ${LOCALES_DIR}/${UTIL_NAME}.pot
 	sed -i -e '4d;10d;$$ d' ${LOCALES_DIR}/${UTIL_NAME}.pot
 
 .PHONY: translate-update

locales/translations/en/LC_MESSAGES/codeplag.po

@@ -1,12 +1,12 @@
 # English translations for codeplag.
-# Copyright (C) 2024-2025 Codeplag Development Team
+# Copyright (C) 2024-2026 Codeplag Development Team
 # This file is distributed under the same license as the codeplag project.
 #
 msgid ""
 msgstr ""
-"Project-Id-Version: codeplag 0.6.1\n"
+"Project-Id-Version: codeplag 0.6.2\n"
 "POT-Creation-Date: 2024-05-21 09:28+0300\n"
-"PO-Revision-Date: 2025-03-28 12:05+0300\n"
+"PO-Revision-Date: 2026-03-23 19:21+0300\n"
 "Last-Translator: Artyom Semidolin\n"
 "Language: en\n"
 "Language-Team: en <LL@li.org>\n"
@@ -286,11 +286,11 @@ msgstr ""
 "The'path-regexp' option requires the provided 'directories', 'github-"
 "user', or 'github-urls' options."
 
-#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:440
+#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:444
 msgid "All paths must be provided."
 msgstr "All or none of the root paths must be specified."
 
-#: src/codeplag/handlers/report.py:437
+#: src/codeplag/handlers/report.py:441
 msgid "Invalid report type."
 msgstr "Invalid report type."
 

locales/translations/ru/LC_MESSAGES/codeplag.po

@@ -1,10 +1,10 @@
 # Russian translations for codeplag.
-# Copyright (C) 2024-2025 Codeplag Development Team
+# Copyright (C) 2024-2026 Codeplag Development Team
 # This file is distributed under the same license as the codeplag project.
 #
 msgid ""
 msgstr ""
-"Project-Id-Version: codeplag 0.6.1\n"
+"Project-Id-Version: codeplag 0.6.2\n"
 "POT-Creation-Date: 2024-05-21 09:28+0300\n"
 "PO-Revision-Date: 2025-03-28 12:05+0300\n"
 "Last-Translator: Artyom Semidolin\n"
@@ -288,22 +288,22 @@ msgstr ""
 "модификации."
 
 #: src/codeplag/codeplagcli.py:443
-msgid "The'repo-regexp' option requires the provided 'github-user' option."
+msgid "The 'repo-regexp' option requires the provided 'github-user' option."
 msgstr "Аргумент 'repo-regexp' требует заданного параметра 'github-user'."
 
 #: src/codeplag/codeplagcli.py:450
 msgid ""
-"The'path-regexp' option requires the provided 'directories', 'github-"
+"The 'path-regexp' option requires the provided 'directories', 'github-"
 "user', or 'github-urls' options."
 msgstr ""
 "Аргумент 'path-regexp' требует заданного параметра 'directories', "
 "'github-user' или 'github-urls'."
 
-#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:440
+#: src/codeplag/codeplagcli.py:460 src/codeplag/handlers/report.py:444
 msgid "All paths must be provided."
 msgstr "Необходимо указать все корневые пути или не указывать ни одного."
 
-#: src/codeplag/handlers/report.py:437
+#: src/codeplag/handlers/report.py:441
 msgid "Invalid report type."
 msgstr "Некорректный тип отчёта."
 

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "codeplag"
-version = "0.6.1"
+version = "0.6.2"
 description = "Code plagiarism searching package."
 authors = [
     { name = "Artyom Semidolin, Dmitry Nikolaev, Alexander Evsikov" }

src/codeplag/codeplagcli.py

@@ -440,14 +440,14 @@ def validate_args(self: Self, parsed_args: argparse.Namespace) -> None:
         elif root == "check":
             if parsed_args.repo_regexp and not parsed_args.github_user:
                 self.error(
-                    _("The'repo-regexp' option requires the provided 'github-user' option.")
+                    _("The 'repo-regexp' option requires the provided 'github-user' option.")
                 )
             elif parsed_args.path_regexp and not (
                 parsed_args.directories or parsed_args.github_user or parsed_args.github_urls
             ):
                 self.error(
                     _(
-                        "The'path-regexp' option requires the provided 'directories', "
+                        "The 'path-regexp' option requires the provided 'directories', "
                         "'github-user', or 'github-urls' options."
                     )
                 )

src/codeplag/cplag/tree.py

@@ -62,3 +62,4 @@ def __add_node_to_structure(features: ASTFeatures, node_name: str, curr_depth: i
         features.from_num[features.count_unodes] = node_name
         features.count_unodes += 1
     features.structure.append(NodeStructurePlace(curr_depth, features.unodes[node_name]))
+    features.count_of_nodes += 1

src/codeplag/cplag/utils.py

@@ -75,6 +75,9 @@ def _get_works_from_filepaths(
                 continue
 
             features = get_features(cursor, filepath)
+            if features.count_of_nodes == 0:
+                codeplag_logger.debug("Skipping the file '%s' due it contains no code.", filepath)
+                continue
             if features_cache is not None:
                 features_cache.save_features(features)
         works.append(features)
@@ -118,6 +121,11 @@ def get_from_content(self: Self, work_info: WorkInfo) -> ASTFeatures | None:
             # hook for correct filtering info while parsing source code
             features = get_features(cursor, tf_path)
             tf_path.unlink()
+            if features.count_of_nodes == 0:
+                self.logger.debug(
+                    "Skipping the file '%s' due it contains no code.", work_info.link
+                )
+                return None
             features.filepath = work_info.link
             features.modify_date = work_info.commit.date
             if self.features_cache is not None:

src/codeplag/handlers/report.py

@@ -181,9 +181,10 @@ def calculate_sources_total_similarity(
 
 def _convert_similarity_matrix_to_percent_matrix(matrix: NDArray) -> NDArray:
     """Convert compliance matrix of size N x M x 2 to percent 2 dimensional matrix."""
-    percent_matrix = np.empty((matrix.shape[0], matrix.shape[1]), dtype=np.float64)
+    columns = 0 if len(matrix.shape) == 1 else matrix.shape[1]
+    percent_matrix = np.empty((matrix.shape[0], columns), dtype=np.float64)
     for i in range(matrix.shape[0]):
-        for j in range(matrix.shape[1]):
+        for j in range(columns):
             percent_matrix[i][j] = round(matrix[i][j][0] / matrix[i][j][1] * 100, 2)
     return percent_matrix
 

src/codeplag/pyplag/utils.py

@@ -119,6 +119,9 @@ def _get_works_from_filepaths(
                 continue
 
             features = get_features_from_ast(tree, filename)
+            if features.count_of_nodes == 0:
+                logger.debug("Skipping the file '%s' due it contains no code.", filename)
+                continue
             if features_cache is not None:
                 features_cache.save_features(features)
         works.append(features)
@@ -152,6 +155,11 @@ def get_from_content(self: Self, work_info: WorkInfo) -> ASTFeatures | None:
             tree = get_ast_from_content(work_info.code, work_info.link)
             if tree is not None:
                 features = get_features_from_ast(tree, work_info.link)
+                if features.count_of_nodes == 0:
+                    self.logger.debug(
+                        "Skipping the file '%s' due it contains no code.", work_info.link
+                    )
+                    return None
                 features.modify_date = work_info.commit.date
                 if self.features_cache is not None:
                     self.features_cache.save_features(features)

src/codeplag/reporters.py

@@ -217,7 +217,10 @@ def deserialize_compare_result_from_dict(result: dict) -> FullCompareInfo:
 
 
 def _deserialize_head_nodes(head_nodes: str) -> list[str]:
-    return [head[1:-1] for head in head_nodes[1:-1].split(", ")]
+    head_nodes_without_brackets = head_nodes[1:-1]
+    if not head_nodes_without_brackets:
+        return []
+    return [head[1:-1] for head in head_nodes_without_brackets.split(", ")]
 
 
 def _deserialize_path(path: str) -> str | Path:

test/auto/functional/test_check.py

@@ -61,7 +61,7 @@ def test_check_util_version():
         ),
         (
             ["--github-urls", *CPP_GITHUB_FILES, CPP_GITHUB_DIR],
-            b"Getting works features from GitHub urls",
+            b"Getting works features from",
             True,
         ),
         (
@@ -143,7 +143,7 @@ def test_check_short_output() -> None:
 )
 def test_check_failed_when_repo_regexp_provided_without_required_args(
     cmd: list[str],
-):
+) -> None:
     result = run_check(cmd + ["--repo-regexp", "something"])
 
     result.assert_argparse_error()
@@ -153,7 +153,6 @@ def test_check_failed_when_repo_regexp_provided_without_required_args(
     "cmd",
     [
         ["--files", *PY_FILES],
-        ["--github-urls", *PY_GITHUB_FILES],
     ],
 )
 def test_check_failed_when_path_regexp_provided_without_required_args(

test/unit/codeplag/cplag/test_tree.py

@@ -89,15 +89,14 @@ def test_generic_visit(first_cursor: Cursor) -> None:
     generic_visit(first_cursor, features)
 
     assert features.filepath == _SAMPLE1_PATH
-    assert features.count_of_nodes == 0
+    assert features.count_of_nodes == len(features.structure) == 23
     assert features.head_nodes == ['gcd']
     assert features.operators == {}
     assert features.keywords == {}
     assert features.literals == {}
     assert len(features.unodes) == 10
     assert len(features.from_num) == 10
     assert features.count_unodes == 10
-    assert len(features.structure) == 23
     assert features.tokens == [8, 10, 10, 202, 205, 114, 100,
                                101, 106, 214, 100, 101, 214,
                                103, 100, 101, 100, 101, 114,
@@ -108,15 +107,14 @@ def test_get_features(second_cursor: Cursor) -> None:
     features = get_features(second_cursor, _SAMPLE2_PATH)
 
     assert features.filepath == _SAMPLE2_PATH
-    assert features.count_of_nodes == 0
+    assert features.count_of_nodes == len(features.structure) == 25
     assert features.head_nodes == ['gcd']
     assert features.operators == {'==': 1, '%': 1}
     assert features.keywords == {'int': 1, 'if': 1, 'return': 2, 'long': 2}
     assert features.literals == {'0L': 1}
     assert len(features.unodes) == 10
     assert len(features.from_num) == 10
     assert features.count_unodes == 10
-    assert len(features.structure) == 25
     assert features.tokens == [8, 10, 10, 202, 205, 114, 100,
                                101, 106, 202, 214, 100, 100,
                                101, 214, 103, 100, 101, 100,
@@ -128,7 +126,7 @@ def test_bad_encoding_syms(third_cursor: Cursor) -> None:
     features = get_features(third_cursor, _SAMPLE3_PATH)
 
     assert features.filepath == _SAMPLE3_PATH
-    assert features.count_of_nodes == 0
+    assert features.count_of_nodes == len(features.structure) == 167
     assert features.head_nodes == ['main']
     # TODO: why so many '<', '>' may be from include, ignore it
     assert features.operators == {'==': 1, '<': 5, '>': 3, '!=': 1, '&': 3, '*': 1, '=': 4}
@@ -139,6 +137,5 @@ def test_bad_encoding_syms(third_cursor: Cursor) -> None:
     assert len(features.unodes) == 18
     assert len(features.from_num) == 18
     assert features.count_unodes == 18
-    assert len(features.structure) == 167
     assert len(features.tokens) == 167
     assert features.sha256 == "236f1b7ea02c3f68e390c7e155fec1a198d4c9ab3d8306d613df8399189291de"

test/unit/codeplag/handlers/test_report.py

@@ -3,6 +3,7 @@
 import numpy as np
 import pandas as pd
 import pytest
+from numpy.typing import NDArray
 
 from codeplag.handlers.report import (
     CntHeadNodes,
@@ -268,7 +269,23 @@ def test__get_resulting_same_percentages(
     assert _get_resulting_same_percentages(same_parts_of_all, cnt_head_nodes) == expected
 
 
-def test__convert_similarity_matrix_to_percent_matrix():
-    assert _convert_similarity_matrix_to_percent_matrix(
-        np.array([[[1, 2], [1, 3], [3, 4]], [[1, 8], [1, 4], [3, 5]]])
-    ).tolist() == [[50.0, 33.33, 75.0], [12.5, 25.0, 60.0]]
+@pytest.mark.parametrize(
+    ("matrix", "result"),
+    [
+        (
+            np.array([[[1, 2], [1, 3], [3, 4]], [[1, 8], [1, 4], [3, 5]]]),
+            [[50.0, 33.33, 75.0], [12.5, 25.0, 60.0]],
+        ),
+        (
+            np.array([]),
+            [],
+        ),
+    ],
+)
+def test__convert_similarity_matrix_to_percent_matrix(matrix: NDArray, result: NDArray) -> None:
+    assert (
+        _convert_similarity_matrix_to_percent_matrix(
+            matrix,
+        ).tolist()
+        == result
+    )

test/unit/codeplag/test_reporters.py

@@ -107,6 +107,7 @@ def test_compare_info_serialize_deserialize(first_compare_result: FullCompareInf
             "['Expr[1]', 'Expr[14]', 'application[16]']",
             ["Expr[1]", "Expr[14]", "application[16]"],
         ),
+        ("[]", []),
     ],
 )
 def test__deserialize_head_nodes(str_head_nodes: str, list_head_nodes: list[str]) -> None: