Merge pull request #1353 from gauravk268/master

Prevent negative total size in Results class when removing duplcates

.github/FUNDING.yml

@@ -1,13 +1 @@
-# These are supported funding model platforms
-
 github: arsenetar
-patreon: # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

.github/workflows/codeql-analysis.yml

@@ -25,11 +25,10 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v2
-
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v1
+        uses: github/codeql-action/init@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
         with:
           languages: ${{ matrix.language }}
           # If you wish to specify custom queries, you can do so here or in a config file.
@@ -44,7 +43,7 @@ jobs:
           make modules
       - if: matrix.language == 'python'
         name: Autobuild
-        uses: github/codeql-action/autobuild@v1
+        uses: github/codeql-action/autobuild@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9
       # Analysis
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v1
+        uses: github/codeql-action/analyze@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v4.31.9

.github/workflows/default.yml

@@ -11,9 +11,9 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Set up Python 3.12
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
         with:
           python-version: "3.12"
       - uses: pre-commit/action@v3.0.1
@@ -23,7 +23,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest]
-        python-version: [3.7, 3.8, 3.9, "3.10", "3.11", "3.12"]
+        python-version: [3.8, 3.9, "3.10", "3.11", "3.12", "3.13", "3.14"]
         include:
           - os: windows-latest
             python-version: "3.12"
@@ -31,9 +31,9 @@ jobs:
             python-version: "3.12"
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Set up Python ${{ matrix.python-version }}
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
@@ -49,7 +49,17 @@ jobs:
           pytest core hscommon
       - name: Upload Artifacts
         if: matrix.os == 'ubuntu-latest'
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: modules ${{ matrix.python-version }}
-          path: ${{ github.workspace }}/**/*.so
+          path: build/**/*.so
+  merge-artifacts:
+    needs: [test]
+    runs-on: ubuntu-latest
+    steps:
+      - name: Merge Artifacts
+        uses: actions/upload-artifact/merge@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
+        with:
+          name: modules
+          pattern: modules*
+          delete-merged: true

.github/workflows/tx-push.yml

@@ -15,7 +15,7 @@ jobs:
   push-source:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Get Transifex Client
         run: |
           curl -o- https://raw.githubusercontent.com/transifex/cli/master/install.sh | bash -s -- $TX_VERSION

.vscode/launch.json

@@ -6,7 +6,7 @@
     "configurations": [
         {
             "name": "DupuGuru",
-            "type": "python",
+            "type": "debugpy",
             "request": "launch",
             "program": "run.py",
             "console": "integratedTerminal",

.vscode/settings.json

@@ -12,5 +12,6 @@
     "[python]": {
         "editor.formatOnSave": true,
         "editor.defaultFormatter": "ms-python.black-formatter"
-    }
+    },
+    "python.testing.pytestEnabled": true
 }

build.py

@@ -10,7 +10,6 @@ from optparse import OptionParser
 import shutil
 from multiprocessing import Pool
 
-from setuptools import sandbox
 from hscommon import sphinxgen
 from hscommon.build import (
     add_to_pythonpath,
@@ -18,6 +17,7 @@ from hscommon.build import (
     fix_qt_resource_file,
 )
 from hscommon import loc
+import subprocess
 
 
 def parse_args():
@@ -118,7 +118,7 @@ def build_normpo():
 def build_pe_modules():
     print("Building PE Modules")
     # Leverage setup.py to build modules
-    sandbox.run_setup("setup.py", ["build_ext", "--inplace"])
+    subprocess.check_call([sys.executable, "setup.py", "build_ext", "--inplace"])
 
 
 def build_normal():

core/pe/cache_sqlite.py

@@ -158,7 +158,7 @@ class SqliteCache:
         ids = ",".join(map(str, rowids))
         sql = (
             "select rowid, blocks, blocks2, blocks3, blocks4, blocks5, blocks6, blocks7, blocks8 "
-            f"from pictures where rowid in {ids}"
+            f"from pictures where rowid in ({ids})"
         )
         cur = self.con.execute(sql)
         return (

core/pe/matchblock.py

@@ -54,7 +54,7 @@ def get_cache(cache_path, readonly=False):
     return SqliteCache(cache_path, readonly=readonly)
 
 
-def prepare_pictures(pictures, cache_path, with_dimensions, j=job.nulljob):
+def prepare_pictures(pictures, cache_path, with_dimensions, match_rotated, j=job.nulljob):
     # The MemoryError handlers in there use logging without first caring about whether or not
     # there is enough memory left to carry on the operation because it is assumed that the
     # MemoryError happens when trying to read an image file, which is freed from memory by the
@@ -76,8 +76,14 @@ def prepare_pictures(pictures, cache_path, with_dimensions, j=job.nulljob):
             if with_dimensions:
                 picture.dimensions  # pre-read dimensions
             try:
-                if picture.unicode_path not in cache:
-                    blocks = [picture.get_blocks(BLOCK_COUNT_PER_SIDE, orientation) for orientation in range(1, 9)]
+                if picture.unicode_path not in cache or (
+                    match_rotated and any(block == [] for block in cache[picture.unicode_path])
+                ):
+                    if match_rotated:
+                        blocks = [picture.get_blocks(BLOCK_COUNT_PER_SIDE, orientation) for orientation in range(1, 9)]
+                    else:
+                        blocks = [[]] * 8
+                        blocks[max(picture.get_orientation() - 1, 0)] = picture.get_blocks(BLOCK_COUNT_PER_SIDE)
                     cache[picture.unicode_path] = blocks
                 prepared.append(picture)
             except (OSError, ValueError) as e:
@@ -187,7 +193,7 @@ def getmatches(pictures, cache_path, threshold, match_scaled=False, match_rotate
         j.set_progress(comparison_count, progress_msg)
 
     j = j.start_subjob([3, 7])
-    pictures = prepare_pictures(pictures, cache_path, with_dimensions=not match_scaled, j=j)
+    pictures = prepare_pictures(pictures, cache_path, not match_scaled, match_rotated, j=j)
     j = j.start_subjob([9, 1], tr("Preparing for matching"))
     cache = get_cache(cache_path)
     id2picture = {}

core/pe/photo.py

@@ -37,7 +37,7 @@ class Photo(fs.File):
     def _plat_get_blocks(self, block_count_per_side, orientation):
         raise NotImplementedError()
 
-    def _get_orientation(self):
+    def get_orientation(self):
         if not hasattr(self, "_cached_orientation"):
             try:
                 with self.path.open("rb") as fp:
@@ -95,13 +95,13 @@ class Photo(fs.File):
         fs.File._read_info(self, field)
         if field == "dimensions":
             self.dimensions = self._plat_get_dimensions()
-            if self._get_orientation() in {5, 6, 7, 8}:
+            if self.get_orientation() in {5, 6, 7, 8}:
                 self.dimensions = (self.dimensions[1], self.dimensions[0])
         elif field == "exif_timestamp":
             self.exif_timestamp = self._get_exif_timestamp()
 
     def get_blocks(self, block_count_per_side, orientation: int = None):
         if orientation is None:
-            return self._plat_get_blocks(block_count_per_side, self._get_orientation())
+            return self._plat_get_blocks(block_count_per_side, self.get_orientation())
         else:
             return self._plat_get_blocks(block_count_per_side, orientation)

core/prioritize.py

@@ -96,6 +96,8 @@ class FilenameCategory(CriterionCategory):
     DOESNT_END_WITH_NUMBER = 1
     LONGEST = 2
     SHORTEST = 3
+    LONGEST_PATH = 4
+    SHORTEST_PATH = 5
 
     def format_criterion_value(self, value):
         return {
@@ -103,6 +105,8 @@ class FilenameCategory(CriterionCategory):
             self.DOESNT_END_WITH_NUMBER: tr("Doesn't end with number"),
             self.LONGEST: tr("Longest"),
             self.SHORTEST: tr("Shortest"),
+            self.LONGEST_PATH: tr("Longest Path"),
+            self.SHORTEST_PATH: tr("Shortest Path"),
         }[value]
 
     def extract_value(self, dupe):
@@ -116,6 +120,10 @@ class FilenameCategory(CriterionCategory):
                 return 0 if ends_with_digit else 1
             else:
                 return 1 if ends_with_digit else 0
+        elif crit_value == self.LONGEST_PATH:
+            return len(str(dupe.folder_path)) * -1
+        elif crit_value == self.SHORTEST_PATH:
+            return len(str(dupe.folder_path))
         else:
             value = len(value)
             if crit_value == self.LONGEST:
@@ -130,6 +138,8 @@ class FilenameCategory(CriterionCategory):
                 self.DOESNT_END_WITH_NUMBER,
                 self.LONGEST,
                 self.SHORTEST,
+                self.LONGEST_PATH,
+                self.SHORTEST_PATH,
             ]
         ]
 

core/results.py

@@ -325,7 +325,7 @@ class Results(Markable):
             del self.__group_of_duplicate[dupe]
             self._remove_mark_flag(dupe)
             self.__total_count -= 1
-            self.__total_size -= dupe.size
+            self.__total_size = max(0, self.__total_size - dupe.size)
             if not group:
                 del self.__group_of_duplicate[ref]
                 self.__groups.remove(group)

core/tests/cache_test.py

@@ -59,13 +59,13 @@ class BaseTestCaseCache:
 
     def test_set_then_retrieve_blocks(self):
         c = self.get_cache()
-        b = [(0, 0, 0), (1, 2, 3)]
+        b = [[(0, 0, 0), (1, 2, 3)]] * 8
         c["foo"] = b
         eq_(b, c["foo"])
 
     def test_delitem(self):
         c = self.get_cache()
-        c["foo"] = ""
+        c["foo"] = [[]] * 8
         del c["foo"]
         assert "foo" not in c
         with raises(KeyError):
@@ -74,16 +74,16 @@ class BaseTestCaseCache:
     def test_persistance(self, tmpdir):
         DBNAME = tmpdir.join("hstest.db")
         c = self.get_cache(str(DBNAME))
-        c["foo"] = [(1, 2, 3)]
+        c["foo"] = [[(1, 2, 3)]] * 8
         del c
         c = self.get_cache(str(DBNAME))
-        eq_([(1, 2, 3)], c["foo"])
+        eq_([[(1, 2, 3)]] * 8, c["foo"])
 
     def test_filter(self):
         c = self.get_cache()
-        c["foo"] = ""
-        c["bar"] = ""
-        c["baz"] = ""
+        c["foo"] = [[]] * 8
+        c["bar"] = [[]] * 8
+        c["baz"] = [[]] * 8
         c.filter(lambda p: p != "bar")  # only 'bar' is removed
         eq_(2, len(c))
         assert "foo" in c
@@ -92,9 +92,9 @@ class BaseTestCaseCache:
 
     def test_clear(self):
         c = self.get_cache()
-        c["foo"] = ""
-        c["bar"] = ""
-        c["baz"] = ""
+        c["foo"] = [[]] * 8
+        c["bar"] = [[]] * 8
+        c["baz"] = [[]] * 8
         c.clear()
         eq_(0, len(c))
         assert "foo" not in c
@@ -104,7 +104,7 @@ class BaseTestCaseCache:
     def test_by_id(self):
         # it's possible to use the cache by referring to the files by their row_id
         c = self.get_cache()
-        b = [(0, 0, 0), (1, 2, 3)]
+        b = [[(0, 0, 0), (1, 2, 3)]] * 8
         c["foo"] = b
         foo_id = c.get_id("foo")
         eq_(c[foo_id], b)
@@ -127,10 +127,10 @@ class TestCaseSqliteCache(BaseTestCaseCache):
         fp.write("invalid sqlite content")
         fp.close()
         c = self.get_cache(dbname)  # should not raise a DatabaseError
-        c["foo"] = [(1, 2, 3)]
+        c["foo"] = [[(1, 2, 3)]] * 8
         del c
         c = self.get_cache(dbname)
-        eq_(c["foo"], [(1, 2, 3)])
+        eq_(c["foo"], [[(1, 2, 3)]] * 8)
 
 
 class TestCaseCacheSQLEscape:
@@ -152,7 +152,7 @@ class TestCaseCacheSQLEscape:
 
     def test_delitem(self):
         c = self.get_cache()
-        c["foo'bar"] = []
+        c["foo'bar"] = [[]] * 8
         try:
             del c["foo'bar"]
         except KeyError: