Funktionalität min_savings der caesiumclt 1.3.0 implementiert (default: 2%), log-Datei um "Bild in Folien Nr." ergänzt.

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:
-- Libcaesium 1.1.0 kann nun auch gif verkleinern
+Änderungen in 1.1.6:
+- Libcaesium 1.3.0 kann nun auch files ignorieren, wenn die Kompression kleiner als <MIN_SAVING> ist
 """
 
 import argparse
@@ -35,11 +35,12 @@ from threading import Lock
 from typing import 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%"
 
 
 # -------------------- Utilities --------------------
@@ -89,7 +90,7 @@ 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 +98,7 @@ 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)]
@@ -121,40 +122,45 @@ 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]]:
-    """
-    Durchsucht alle .rels-Dateien im angegebenen Verzeichnis und gibt die Slide-Nummern zurück,
-    in denen die angegebene Bilddatei referenziert wird.
+def build_image_slide_index(rels_dir: Path) -> dict[str, List[int]]:
+    if not rels_dir.exists() or not rels_dir.is_dir():
+        return {}
 
-    :param rels_dir: Pfad zum Verzeichnis ppt/slides/_rels
-    :param image_filename: z. B. 'image80.png'
-    :return: Liste von Slide-Nummern oder None
-    """
-    slide_numbers = []
+    image_to_slides: dict[str, set[int]] = {}
 
-    for rels_file in os.listdir(rels_dir):
-        if rels_file.startswith("slide") and rels_file.endswith(".xml.rels"):
-            rels_path = os.path.join(rels_dir, rels_file)
+    for rels_path in rels_dir.iterdir():
+        rels_file = rels_path.name
+        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:
-                        match = re.search(r"slide(\d+).xml.rels", rels_file)
-                        if match:
-                            slide_number = int(match.group(1))
-                            slide_numbers.append(slide_number)
-            except ET.ParseError:
-                print(f"Fehler beim Parsen von {rels_file}")
+                    image_name = Path(target).name
+                    if image_name:
+                        if image_name not in image_to_slides:
+                            image_to_slides[image_name] = set()
+                        image_to_slides[image_name].add(slide_number)
+            except (ET.ParseError, OSError):
+                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
 
 
 
 
 # -------------------- 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) -> dict:
     start_time = time.perf_counter()
     result = {
         "input": str(input_pptx),
@@ -188,6 +194,7 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
             z.extractall(work_dir)
 
         slides_dir  = work_dir / "ppt" / "slides"
+        rels_dir = slides_dir / "_rels"
         media_dir = work_dir / "ppt" / "media"
         
         images = []
@@ -207,23 +214,23 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
         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()
             orig_size = img_path.stat().st_size
             chosen_size = orig_size
-            found_in_slide=None
-            slide_nr=""
+            found_in_slide = None
+            slide_nr = ""
 
             try:
-                found_in_slide = get_slide_numbers_for_image(slides_dir.name, img_path.name) 
+                found_in_slide = image_to_slides.get(img_path.name)
                 if found_in_slide is None:
                     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)
+                caesium_out = compress_with_caesium(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:
@@ -359,15 +366,16 @@ 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()
 
@@ -412,7 +420,7 @@ 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']:
                 successes += 1
                 overall_before += res['size_before']
@@ -427,7 +435,7 @@ 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']:
             successes += 1
             overall_before += res['size_before']