Refactor and UnitTest

.gitignore

@@ -2,3 +2,4 @@ python-3.*-embed-amd64.zip
 python-embed/*
 .vscode/launch.json
 logs/*.log
+__pycache__/*

.vscode/settings.json

@@ -0,0 +1,11 @@
+{
+    "python.testing.unittestArgs": [
+        "-v",
+        "-s",
+        ".",
+        "-p",
+        "test_*.py"
+    ],
+    "python.testing.pytestEnabled": false,
+    "python.testing.unittestEnabled": true
+}

pptx_image_compress.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 """
 PPTX Grafik-Komprimier-Tool (nur CaesiumCLT, Multi-Thread, Batch, sauberes Cleanup)
-Version: 1.1.4
+Version: 1.1.6
 
 
 Highlights:
@@ -12,8 +12,8 @@ Highlights:
 - Log: image_name,size_before,size_after,saving,saving_percent
 - Summary inkl. Zeit benötigt
 
-Änderungen in 1.1.4:
+Änderungen in 1.1.6:
-- Libcaesium 1.1.0 kann nun auch gif verkleinern
+- Libcaesium 1.3.0 kann nun auch files ignorieren, wenn die Kompression kleiner als <MIN_SAVING> ist
 """
 
 import argparse
@@ -32,14 +32,51 @@ from pathlib import Path
 from datetime import timedelta
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from threading import Lock
-from typing import List, Optional
+from dataclasses import dataclass
+from typing import Callable, List, Optional
 
 
-__version__ = "1.1.4"
+__version__ = "1.1.6"
 
 ALLOWED_EXT = {".jpg", ".jpeg", ".png", ".webp", ".gif"}
 PROGRESS_BAR_LEN = 40
 TEMP_PREFIX = "pptx_compress_"
+DEFAULT_MIN_SAVINGS = "2%"
+
+
+@dataclass
+class DeckResult:
+    input: str
+    output: str
+    ok: bool = False
+    size_before: int = 0
+    size_after: int = 0
+    elapsed_sec: float = 0.0
+    error: Optional[str] = None
+    log_file: Optional[str] = None
+
+
+@dataclass
+class ImageProcessResult:
+    image_name: str
+    orig_size: int
+    chosen_size: int
+    slide_nr: str
+
+
+def discover_images(media_dir: Path) -> list[Path]:
+    images: list[Path] = []
+    if media_dir.exists():
+        for f in sorted(media_dir.iterdir()):
+            if f.is_file() and f.suffix.lower() in ALLOWED_EXT:
+                images.append(f)
+    return images
+
+
+def image_result_to_log_line(image_result: ImageProcessResult) -> str:
+    saving = image_result.orig_size - image_result.chosen_size
+    saving_percent = round((saving / image_result.orig_size) * 100, 2) if image_result.orig_size > 0 else 0.0
+    return f"{image_result.image_name};{human_kb(image_result.orig_size)};{human_kb(image_result.chosen_size)};{human_kb(saving)};{saving_percent};{image_result.slide_nr}\n"
 
 
 # -------------------- Utilities --------------------
@@ -89,7 +126,7 @@ def zip_dir_to_pptx(src_dir: Path, out_pptx: Path):
 def which(cmd: str):
     return shutil.which(cmd)
 
-def compress_with_caesium(original: Path, out_dir: Path, caesium_threads: int | None, quality: int) -> Path | None:
+def compress_with_caesium(original: Path, out_dir: Path, caesium_threads: int | None, quality: int, min_savings: str) -> Path | None:
     exe = which("caesiumclt")
     if not exe:
         raise RuntimeError("[ERROR] 'caesiumclt' wurde nicht gefunden. Bitte CaesiumCLT installieren und in PATH verfügbar machen.")
@@ -97,7 +134,7 @@ def compress_with_caesium(original: Path, out_dir: Path, caesium_threads: int |
     ext = original.suffix.lower()
     if ext not in {".jpg", ".jpeg", ".png", ".webp", ".gif"}:
         return None
-    cmd = [exe, "-q", str(quality), "-O", "bigger", "-o", str(out_dir)]
+    cmd = [exe, "-q", str(quality), "-O", "bigger", "--min-savings", min_savings, "-o", str(out_dir)]
     if caesium_threads is not None:
         cmd += ["--threads", str(caesium_threads)]
     cmd += [str(original)]
@@ -121,51 +158,91 @@ def format_duration(seconds: float) -> str:
         return f"{hms}.{frac[:2]}"
     return base
 
-def get_slide_numbers_for_image(rels_dir: str, image_filename: str) -> Optional[List[int]]:
+def build_image_slide_index(rels_dir: Path) -> dict[str, List[int]]:
-    """
+    if not rels_dir.exists() or not rels_dir.is_dir():
-    Durchsucht alle .rels-Dateien im angegebenen Verzeichnis und gibt die Slide-Nummern zurück,
+        return {}
-    in denen die angegebene Bilddatei referenziert wird.
 
-    :param rels_dir: Pfad zum Verzeichnis ppt/slides/_rels
+    image_to_slides: dict[str, set[int]] = {}
-    :param image_filename: z. B. 'image80.png'
-    :return: Liste von Slide-Nummern oder None
-    """
-    slide_numbers = []
 
-    for rels_file in os.listdir(rels_dir):
+    for rels_path in rels_dir.iterdir():
-        if rels_file.startswith("slide") and rels_file.endswith(".xml.rels"):
+        rels_file = rels_path.name
-            rels_path = os.path.join(rels_dir, rels_file)
+        if rels_file.startswith("slide") and rels_file.endswith(".xml.rels") and rels_path.is_file():
+            match = re.search(r"slide(\d+)\.xml\.rels$", rels_file)
+            if not match:
+                continue
+            slide_number = int(match.group(1))
             try:
                 tree = ET.parse(rels_path)
                 root = tree.getroot()
                 for rel in root.findall(".//{http://schemas.openxmlformats.org/package/2006/relationships}Relationship"):
                     target = rel.attrib.get("Target", "")
-                    if image_filename in target:
+                    image_name = Path(target).name
-                        match = re.search(r"slide(\d+).xml.rels", rels_file)
+                    if image_name:
-                        if match:
+                        if image_name not in image_to_slides:
-                            slide_number = int(match.group(1))
+                            image_to_slides[image_name] = set()
-                            slide_numbers.append(slide_number)
+                        image_to_slides[image_name].add(slide_number)
-            except ET.ParseError:
+            except (ET.ParseError, OSError):
-                print(f"Fehler beim Parsen von {rels_file}")
+                print(f"Fehler beim Lesen von {rels_file}")
 
-    return slide_numbers if slide_numbers else None
+    return {img: sorted(slides) for img, slides in image_to_slides.items()}
 
 
+def get_slide_numbers_for_image(rels_dir: Path, image_filename: str) -> Optional[List[int]]:
+    image_to_slides = build_image_slide_index(rels_dir)
+    slides = image_to_slides.get(image_filename)
+    return slides if slides else None
+
+
+def process_image_file(
+    idx: int,
+    img_path: Path,
+    scratch_dir: Path,
+    image_to_slides: dict[str, List[int]],
+    caesium_threads: int | None,
+    quality: int,
+    min_savings: str,
+    compressor: Callable[[Path, Path, int | None, int, str], Path | None],
+) -> ImageProcessResult:
+    orig_size = img_path.stat().st_size
+    chosen_size = orig_size
+    found_in_slide = image_to_slides.get(img_path.name)
+    slide_nr = "NOT_USED" if found_in_slide is None else str(found_in_slide)
+
+    try:
+        out_sub = scratch_dir / f"img_{idx:06d}"
+        caesium_out = compressor(img_path, out_sub, caesium_threads, quality, min_savings)
+        if caesium_out and caesium_out.exists():
+            s = caesium_out.stat().st_size
+            if s < orig_size:
+                tmp_target = img_path.with_suffix(img_path.suffix + ".tmp")
+                shutil.copy2(caesium_out, tmp_target)
+                tmp_target.replace(img_path)
+                chosen_size = s
+    except Exception:
+        chosen_size = orig_size
+
+    return ImageProcessResult(
+        image_name=img_path.name,
+        orig_size=orig_size,
+        chosen_size=chosen_size,
+        slide_nr=slide_nr,
+    )
 
 
 # -------------------- Core per-deck processing --------------------
-def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quality: int) -> dict:
+def process_single_deck(
+    input_pptx: Path,
+    output_pptx: Path,
+    threads: int,
+    quality: int,
+    min_savings: str,
+    compressor: Callable[[Path, Path, int | None, int, str], Path | None] = compress_with_caesium,
+) -> DeckResult:
     start_time = time.perf_counter()
-    result = {
+    result = DeckResult(
-        "input": str(input_pptx),
+        input=str(input_pptx),
-        "output": str(output_pptx),
+        output=str(output_pptx),
-        "ok": False,
+    )
-        "size_before": 0,
-        "size_after": 0,
-        "elapsed_sec": 0.0,
-        "error": None,
-        "log_file": None,
-    }
 
     try:
         if not input_pptx.exists() or input_pptx.suffix.lower() != ".pptx":
@@ -182,63 +259,44 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
         log_lines = ["image_name;size_before(kb);size_after(kb);saving(kb);saving_percent(%);in_slide_number\n"]
 
         size_before = input_pptx.stat().st_size
-        result["size_before"] = size_before
+        result.size_before = size_before
 
         with zipfile.ZipFile(input_pptx, "r") as z:
             z.extractall(work_dir)
 
         slides_dir  = work_dir / "ppt" / "slides"
+        rels_dir = slides_dir / "_rels"
         media_dir = work_dir / "ppt" / "media"
 
-        images = []
+        images = discover_images(media_dir)
-
-        if media_dir.exists():
-            for f in sorted(media_dir.iterdir()):
-                if f.is_file() and f.suffix.lower() in ALLOWED_EXT:
-                    images.append(f)
 
         total = len(images)
         print(f"[Processing] {input_pptx.name}: {total} Bild(er) gefunden")
         print_progress(0, total)
 
-        if not which("caesiumclt"):
+        if not which("caesiumclt") and compressor is compress_with_caesium:
             raise RuntimeError("'caesiumclt' nicht gefunden. Bitte installieren und in PATH verfügbar machen.")
 
         caesium_threads = 1 if threads and threads > 1 else None
         lock = Lock()
         done_count = 0
+        image_to_slides = build_image_slide_index(rels_dir)
 
         def worker(idx: int, img_path: Path):
             nonlocal done_count
-            ext = img_path.suffix.lower()
+            image_result = process_image_file(
-            orig_size = img_path.stat().st_size
+                idx=idx,
-            chosen_size = orig_size
+                img_path=img_path,
-            found_in_slide=None
+                scratch_dir=scratch_dir,
-            slide_nr=""
+                image_to_slides=image_to_slides,
-
+                caesium_threads=caesium_threads,
-            try:
+                quality=quality,
-                found_in_slide = get_slide_numbers_for_image(slides_dir.name, img_path.name) 
+                min_savings=min_savings,
-                if found_in_slide is None:
+                compressor=compressor,
-                    slide_nr = "NOT_USED"
+            )
-                else:
-                    slide_nr = str(found_in_slide)
-                out_sub = scratch_dir / f"img_{idx:06d}"
-                caesium_out = compress_with_caesium(img_path, out_sub, caesium_threads, quality)
-                if caesium_out and caesium_out.exists():
-                    s = caesium_out.stat().st_size
-                    if s < orig_size:
-                        tmp_target = img_path.with_suffix(img_path.suffix + ".tmp")
-                        shutil.copy2(caesium_out, tmp_target)
-                        tmp_target.replace(img_path)
-                        chosen_size = s
-            except Exception:
-                chosen_size = orig_size
-            finally:
-                saving = orig_size - chosen_size
-                saving_percent = round((saving / orig_size) * 100, 2) if orig_size > 0 else 0.0
 
             with lock:
-                    log_lines.append(f"{img_path.name};{human_kb(orig_size)};{human_kb(chosen_size)};{human_kb(saving)};{saving_percent};{slide_nr}\n")
+                log_lines.append(image_result_to_log_line(image_result))
                 done_count += 1
                 print_progress(done_count, total)
 
@@ -268,7 +326,7 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
 
         zip_dir_to_pptx(work_dir, output_pptx)
         size_after = output_pptx.stat().st_size
-        result["size_after"] = size_after
+        result.size_after = size_after
 
         try:
             with open(log_file, "w", encoding="utf-8") as f:
@@ -277,9 +335,9 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
             pass
 
         elapsed = time.perf_counter() - start_time
-        result["elapsed_sec"] = elapsed
+        result.elapsed_sec = elapsed
-        result["log_file"] = str(log_file)
+        result.log_file = str(log_file)
-        result["ok"] = True
+        result.ok = True
 
         savings_pct = 0.0 if size_before == 0 else round(100.0 * (size_before - size_after) / size_before, 2)
         print(f"[OK] Fertig!  ({input_pptx.name})")
@@ -291,7 +349,7 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
         print("  Log:       ", log_file)
 
     except Exception as e:
-        result["error"] = str(e)
+        result.error = str(e)
     finally:
         try:
             shutil.rmtree(work_dir, ignore_errors=True)  # type: ignore[name-defined]
@@ -359,15 +417,16 @@ def main():
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
     parser.add_argument('-i','--input', nargs='*', help='Input-PPTX (eine oder mehrere, Wildcards erlaubt). Bei mehreren: -O erforderlich.')
+    parser.add_argument('--input-dir', help='Eingabe-Verzeichnis (optional, für Batch)')
     parser.add_argument('-o','--output', help='Output-PPTX (nur Single-Mode)')
     parser.add_argument('-O','--output-dir', help='Output-Verzeichnis (erforderlich für Batch)')
-    parser.add_argument('--input-dir', help='Eingabe-Verzeichnis (optional, für Batch)')
     parser.add_argument('--pattern', default='*.pptx', help='Dateimuster für --input-dir')
     parser.add_argument('--recursive', action='store_true', help='Rekursiv in --input-dir suchen')
     #parser.add_argument('-t','--threads', type=int, default=min(32, os.cpu_count() or 4), help='Anzahl paralleler Threads pro Datei')
     parser.add_argument('-t','--threads', type=int, default=16, help='Anzahl paralleler Threads pro Datei')
     parser.add_argument('-q','--quality', type=int, default=90, help='Qualität für caesiumclt (0..100), höher = bessere Qualität / größere Datei')
-    parser.add_argument('--version', action='version', version=f'%(prog)s {__version__}')
+    parser.add_argument('--min-savings', default=DEFAULT_MIN_SAVINGS, help="Mindestersparnis für caesiumclt (z. B. 2%%, 100KB, 1MB oder Bytes als Zahl)")
+    parser.add_argument('--version', action='version', version=f'%(prog)s {__version__}',  help="Zeigt die Versionsnummer an" )
     
     args = parser.parse_args()
 
@@ -412,14 +471,14 @@ def main():
                 failures += 1
                 continue
             dst = out_dir / f"{src.stem}_compressed.pptx"
-            res = process_single_deck(src, dst, args.threads, args.quality)
+            res = process_single_deck(src, dst, args.threads, args.quality, args.min_savings)
-            if res['ok']:
+            if res.ok:
                 successes += 1
-                overall_before += res['size_before']
+                overall_before += res.size_before
-                overall_after += res['size_after']
+                overall_after += res.size_after
             else:
                 failures += 1
-                print(f"  Fehler: {src.name} -> {res['error']}")
+                print(f"  Fehler: {src.name} -> {res.error}")
     else:
         src = input_files[0]
         if args.output_dir:
@@ -427,14 +486,14 @@ def main():
             dst = Path(args.output_dir) / f"{src.stem}_compressed.pptx"
         else:
             dst = Path(args.output).resolve() if args.output else src.with_name(f"{src.stem}_compressed.pptx")
-        res = process_single_deck(src, dst, args.threads, args.quality)
+        res = process_single_deck(src, dst, args.threads, args.quality, args.min_savings)
-        if res['ok']:
+        if res.ok:
             successes += 1
-            overall_before += res['size_before']
+            overall_before += res.size_before
-            overall_after += res['size_after']
+            overall_after += res.size_after
         else:
             failures += 1
-            print(f"  Fehler: {src.name} -> {res['error']}")
+            print(f"  Fehler: {src.name} -> {res.error}")
 
     if batch_mode:
             

test_pptx_image_compress.py

@@ -0,0 +1,144 @@
+import tempfile
+import unittest
+import zipfile
+from pathlib import Path
+
+import pptx_image_compress as pic
+
+
+class TestPptxImageCompress(unittest.TestCase):
+    def test_discover_images_filters_extensions(self):
+        with tempfile.TemporaryDirectory() as td:
+            media_dir = Path(td)
+            (media_dir / "a.jpg").write_bytes(b"1")
+            (media_dir / "b.png").write_bytes(b"1")
+            (media_dir / "c.txt").write_bytes(b"1")
+            (media_dir / "d.GIF").write_bytes(b"1")
+            images = pic.discover_images(media_dir)
+            self.assertEqual([p.name for p in images], ["a.jpg", "b.png", "d.GIF"])
+
+    def test_image_result_to_log_line(self):
+        image_result = pic.ImageProcessResult(
+            image_name="image1.png",
+            orig_size=1000,
+            chosen_size=800,
+            slide_nr="[1, 2]",
+        )
+        line = pic.image_result_to_log_line(image_result)
+        self.assertIn("image1.png", line)
+        self.assertIn("[1, 2]", line)
+        self.assertIn("20.0", line)
+
+    def test_process_image_file_replaces_when_smaller(self):
+        with tempfile.TemporaryDirectory() as td:
+            root = Path(td)
+            img = root / "image1.png"
+            img.write_bytes(b"A" * 100)
+            scratch = root / "scratch"
+
+            def fake_compressor(original: Path, out_dir: Path, caesium_threads: int | None, quality: int, min_savings: str):
+                out_dir.mkdir(parents=True, exist_ok=True)
+                out = out_dir / original.name
+                out.write_bytes(b"B" * 40)
+                return out
+
+            result = pic.process_image_file(
+                idx=1,
+                img_path=img,
+                scratch_dir=scratch,
+                image_to_slides={"image1.png": [1]},
+                caesium_threads=1,
+                quality=90,
+                min_savings="2%",
+                compressor=fake_compressor,
+            )
+
+            self.assertEqual(result.chosen_size, 40)
+            self.assertEqual(img.stat().st_size, 40)
+            self.assertEqual(result.slide_nr, "[1]")
+
+    def test_process_image_file_keeps_original_when_bigger(self):
+        with tempfile.TemporaryDirectory() as td:
+            root = Path(td)
+            img = root / "image1.png"
+            img.write_bytes(b"A" * 100)
+            scratch = root / "scratch"
+
+            def fake_compressor(original: Path, out_dir: Path, caesium_threads: int | None, quality: int, min_savings: str):
+                out_dir.mkdir(parents=True, exist_ok=True)
+                out = out_dir / original.name
+                out.write_bytes(b"B" * 120)
+                return out
+
+            result = pic.process_image_file(
+                idx=1,
+                img_path=img,
+                scratch_dir=scratch,
+                image_to_slides={},
+                caesium_threads=1,
+                quality=90,
+                min_savings="2%",
+                compressor=fake_compressor,
+            )
+
+            self.assertEqual(result.chosen_size, 100)
+            self.assertEqual(img.stat().st_size, 100)
+            self.assertEqual(result.slide_nr, "NOT_USED")
+
+    def test_process_single_deck_with_injected_compressor(self):
+        with tempfile.TemporaryDirectory() as td:
+            root = Path(td)
+            input_pptx = root / "input.pptx"
+            output_pptx = root / "output.pptx"
+            source_tree = root / "src"
+            rels_dir = source_tree / "ppt" / "slides" / "_rels"
+            media_dir = source_tree / "ppt" / "media"
+            rels_dir.mkdir(parents=True, exist_ok=True)
+            media_dir.mkdir(parents=True, exist_ok=True)
+
+            rels_xml = (
+                "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
+                "<Relationships xmlns=\"http://schemas.openxmlformats.org/package/2006/relationships\">"
+                "<Relationship Id=\"rId2\" Type=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships/image\" Target=\"../media/image1.png\"/>"
+                "</Relationships>"
+            )
+            (rels_dir / "slide1.xml.rels").write_text(rels_xml, encoding="utf-8")
+            (media_dir / "image1.png").write_bytes(b"A" * 100)
+
+            with zipfile.ZipFile(input_pptx, "w", compression=zipfile.ZIP_DEFLATED) as z:
+                for p in source_tree.rglob("*"):
+                    if p.is_file():
+                        z.write(p, arcname=str(p.relative_to(source_tree)))
+
+            def fake_compressor(original: Path, out_dir: Path, caesium_threads: int | None, quality: int, min_savings: str):
+                out_dir.mkdir(parents=True, exist_ok=True)
+                out = out_dir / original.name
+                out.write_bytes(b"B" * 50)
+                return out
+
+            result = pic.process_single_deck(
+                input_pptx=input_pptx,
+                output_pptx=output_pptx,
+                threads=2,
+                quality=90,
+                min_savings="2%",
+                compressor=fake_compressor,
+            )
+
+            self.assertTrue(result.ok)
+            self.assertEqual(result.error, None)
+            self.assertTrue(output_pptx.exists())
+            self.assertIsNotNone(result.log_file)
+            with zipfile.ZipFile(output_pptx, "r") as z:
+                out_image = z.read("ppt/media/image1.png")
+            self.assertEqual(len(out_image), 50)
+            log_file = result.log_file
+            if log_file is None:
+                self.fail("log_file should not be None")
+            log_text = Path(log_file).read_text(encoding="utf-8")
+            self.assertIn("image1.png", log_text)
+            self.assertIn("[1]", log_text)
+
+
+if __name__ == "__main__":
+    unittest.main()