9 Commits

7 changed files with 217 additions and 32 deletions

1
.gitignore vendored
View File

@@ -1,3 +1,4 @@
python-3.*-embed-amd64.zip python-3.*-embed-amd64.zip
python-embed/* python-embed/*
.vscode/launch.json .vscode/launch.json
logs/*.log

View File

@@ -1,6 +1,6 @@
# PPTX Image Compressor (CaesiumCLT only) # PPTX Image Compressor (CaesiumCLT only)
**Version 1.1.2** **Version 1.1.4**
Dieses Paket enthält: Dieses Paket enthält:
@@ -32,14 +32,13 @@ Die Batch lädt bei Bedarf automatisch das **Windows Embeddable Python Package**
## Was das Tool macht ## Was das Tool macht
- Entpackt die PPTX in einen TempOrdner - Entpackt die PPTX in einen TempOrdner
- Komprimiert **JPG/JPEG, PNG, WebP** mit **CaesiumCLT** (Default `-q 90`, `-O bigger`) - Komprimiert **JPG/JPEG, PNG, WebP, GIF** mit **CaesiumCLT** (Default `-q 90`, `-O bigger`)
- Ersetzt Bilder nur, wenn die komprimierte Datei kleiner ist - Ersetzt Bilder nur, wenn die komprimierte Datei kleiner ist
- Schreibt ein CSVLog (`.log` neben der OutputPPTX) - Schreibt ein CSVLog (`.log` neben der OutputPPTX)
- Baut eine neue PPTX und zeigt eine Summary (Name, Größe vorher/nachher, Ersparnis %, Zeit) - Baut eine neue PPTX und zeigt eine Summary (Name, Größe vorher/nachher, Ersparnis %, Zeit)
- Räumt alle temporären Dateien auf (keine CaesiumTempfiles in der finalen PPTX) - Räumt alle temporären Dateien auf (keine CaesiumTempfiles in der finalen PPTX)
## Hinweise ## Hinweise
- **GIF** wird übersprungen (keine Rekodierung).
- `-t` steuert die Parallelität der PythonThreads; intern wird `caesiumclt --threads 1` gesetzt, sobald `-t > 1`, um Oversubscription zu vermeiden. Default ist 16 - `-t` steuert die Parallelität der PythonThreads; intern wird `caesiumclt --threads 1` gesetzt, sobald `-t > 1`, um Oversubscription zu vermeiden. Default ist 16
- `-q` steuert das Qualitätslevel; intern wird `caesiumclt -q` mit diesem Wert von `0..100` benutzt, Default ist 90 - `-q` steuert das Qualitätslevel; intern wird `caesiumclt -q` mit diesem Wert von `0..100` benutzt, Default ist 90
- Die Batch **verwendet bevorzugt das Embeddable Python** neben der BAT; ansonsten sucht sie echte `python.exe`/`py.exe` im PATH, **ignoriert** aber die MicrosoftStoreAliasPfade (`WindowsApps`). - Die Batch **verwendet bevorzugt das Embeddable Python** neben der BAT; ansonsten sucht sie echte `python.exe`/`py.exe` im PATH, **ignoriert** aber die MicrosoftStoreAliasPfade (`WindowsApps`).

Binary file not shown.

View File

@@ -12,7 +12,7 @@ set "SELF_DIR=%~dp0"
set "SCRIPT=%SELF_DIR%pptx_image_compress.py" set "SCRIPT=%SELF_DIR%pptx_image_compress.py"
rem ---- Python Embeddable config ---- rem ---- Python Embeddable config ----
set "PY_EMBED_VERSION=3.13.7" set "PY_EMBED_VERSION=3.14.4"
set "PY_EMBED_ZIP=python-%PY_EMBED_VERSION%-embed-amd64.zip" set "PY_EMBED_ZIP=python-%PY_EMBED_VERSION%-embed-amd64.zip"
set "PY_EMBED_URL=https://www.python.org/ftp/python/%PY_EMBED_VERSION%/%PY_EMBED_ZIP%" set "PY_EMBED_URL=https://www.python.org/ftp/python/%PY_EMBED_VERSION%/%PY_EMBED_ZIP%"
set "PY_DIR=%SELF_DIR%python-embed" set "PY_DIR=%SELF_DIR%python-embed"

View File

@@ -2,7 +2,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
""" """
PPTX Grafik-Komprimier-Tool (nur CaesiumCLT, Multi-Thread, Batch, sauberes Cleanup) PPTX Grafik-Komprimier-Tool (nur CaesiumCLT, Multi-Thread, Batch, sauberes Cleanup)
Version: 1.1.2 Version: 1.1.4
Highlights: Highlights:
@@ -12,13 +12,14 @@ Highlights:
- Log: image_name,size_before,size_after,saving,saving_percent - Log: image_name,size_before,size_after,saving,saving_percent
- Summary inkl. Zeit benötigt - Summary inkl. Zeit benötigt
Änderungen in 1.1.2: Änderungen in 1.1.4:
- Batch Mode hinzugefügt - Libcaesium 1.1.0 kann nun auch gif verkleinern
- Shellscript-Fix (Store-Alias vermeiden) und Doku-Anpassungen
""" """
import argparse import argparse
import os import os
import re
import xml.etree.ElementTree as ET
import sys import sys
import zipfile import zipfile
import tempfile import tempfile
@@ -31,10 +32,12 @@ from pathlib import Path
from datetime import timedelta from datetime import timedelta
from concurrent.futures import ThreadPoolExecutor, as_completed from concurrent.futures import ThreadPoolExecutor, as_completed
from threading import Lock from threading import Lock
from typing import List, Optional
__version__ = "1.1.2"
ALLOWED_EXT = {".jpg", ".jpeg", ".png", ".webp", ".gif"} # GIF wird übersprungen __version__ = "1.1.4"
ALLOWED_EXT = {".jpg", ".jpeg", ".png", ".webp", ".gif"}
PROGRESS_BAR_LEN = 40 PROGRESS_BAR_LEN = 40
TEMP_PREFIX = "pptx_compress_" TEMP_PREFIX = "pptx_compress_"
@@ -43,6 +46,9 @@ TEMP_PREFIX = "pptx_compress_"
def human_mb(nbytes: int) -> float: def human_mb(nbytes: int) -> float:
return round(nbytes / (1024 * 1024), 2) return round(nbytes / (1024 * 1024), 2)
def human_kb(nbytes: int) -> float:
return round(nbytes / 1024,2)
def ensure_clean_file(path: Path): def ensure_clean_file(path: Path):
if path.exists(): if path.exists():
try: try:
@@ -86,10 +92,10 @@ def which(cmd: str):
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) -> Path | None:
exe = which("caesiumclt") exe = which("caesiumclt")
if not exe: if not exe:
raise RuntimeError(" 'caesiumclt' wurde nicht gefunden. Bitte CaesiumCLT installieren und in PATH verfügbar machen.") raise RuntimeError("[ERROR] 'caesiumclt' wurde nicht gefunden. Bitte CaesiumCLT installieren und in PATH verfügbar machen.")
out_dir.mkdir(parents=True, exist_ok=True) out_dir.mkdir(parents=True, exist_ok=True)
ext = original.suffix.lower() ext = original.suffix.lower()
if ext not in {".jpg", ".jpeg", ".png", ".webp"}: if ext not in {".jpg", ".jpeg", ".png", ".webp", ".gif"}:
return None return None
cmd = [exe, "-q", str(quality), "-O", "bigger", "-o", str(out_dir)] cmd = [exe, "-q", str(quality), "-O", "bigger", "-o", str(out_dir)]
if caesium_threads is not None: if caesium_threads is not None:
@@ -115,6 +121,38 @@ def format_duration(seconds: float) -> str:
return f"{hms}.{frac[:2]}" return f"{hms}.{frac[:2]}"
return base 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.
: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 = []
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)
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}")
return slide_numbers if slide_numbers else None
# -------------------- Core per-deck processing -------------------- # -------------------- 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) -> dict:
start_time = time.perf_counter() start_time = time.perf_counter()
@@ -139,9 +177,9 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
work_dir = Path(tempfile.mkdtemp(prefix=TEMP_PREFIX + "work_")) work_dir = Path(tempfile.mkdtemp(prefix=TEMP_PREFIX + "work_"))
scratch_dir = Path(tempfile.mkdtemp(prefix=TEMP_PREFIX + "scratch_")) scratch_dir = Path(tempfile.mkdtemp(prefix=TEMP_PREFIX + "scratch_"))
log_file = output_pptx.with_suffix(".log") log_file = output_pptx.with_suffix(".log.csv")
ensure_clean_file(log_file) ensure_clean_file(log_file)
log_lines = ["image_name,size_before,size_after,saving,saving_percent"] 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 size_before = input_pptx.stat().st_size
result["size_before"] = size_before result["size_before"] = size_before
@@ -149,15 +187,18 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
with zipfile.ZipFile(input_pptx, "r") as z: with zipfile.ZipFile(input_pptx, "r") as z:
z.extractall(work_dir) z.extractall(work_dir)
slides_dir = work_dir / "ppt" / "slides"
media_dir = work_dir / "ppt" / "media" media_dir = work_dir / "ppt" / "media"
images = [] images = []
if media_dir.exists(): if media_dir.exists():
for f in sorted(media_dir.iterdir()): for f in sorted(media_dir.iterdir()):
if f.is_file() and f.suffix.lower() in ALLOWED_EXT: if f.is_file() and f.suffix.lower() in ALLOWED_EXT:
images.append(f) images.append(f)
total = len(images) total = len(images)
print(f"🔧 {input_pptx.name}: {total} Bild(er) gefunden") print(f"[Processing] {input_pptx.name}: {total} Bild(er) gefunden")
print_progress(0, total) print_progress(0, total)
if not which("caesiumclt"): if not which("caesiumclt"):
@@ -171,14 +212,16 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
nonlocal done_count nonlocal done_count
ext = img_path.suffix.lower() ext = img_path.suffix.lower()
orig_size = img_path.stat().st_size orig_size = img_path.stat().st_size
if ext == ".gif":
with lock:
done_count += 1
log_lines.append(f"{img_path.name},{orig_size},{orig_size},0,0.0")
print_progress(done_count, total)
return
chosen_size = orig_size chosen_size = orig_size
found_in_slide=None
slide_nr=""
try: try:
found_in_slide = get_slide_numbers_for_image(slides_dir.name, 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}" 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)
if caesium_out and caesium_out.exists(): if caesium_out and caesium_out.exists():
@@ -193,8 +236,9 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
finally: finally:
saving = orig_size - chosen_size saving = orig_size - chosen_size
saving_percent = round((saving / orig_size) * 100, 2) if orig_size > 0 else 0.0 saving_percent = round((saving / orig_size) * 100, 2) if orig_size > 0 else 0.0
with lock: with lock:
log_lines.append(f"{img_path.name},{orig_size},{chosen_size},{saving},{saving_percent}") log_lines.append(f"{img_path.name};{human_kb(orig_size)};{human_kb(chosen_size)};{human_kb(saving)};{saving_percent};{slide_nr}\n")
done_count += 1 done_count += 1
print_progress(done_count, total) print_progress(done_count, total)
@@ -238,8 +282,8 @@ def process_single_deck(input_pptx: Path, output_pptx: Path, threads: int, quali
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) savings_pct = 0.0 if size_before == 0 else round(100.0 * (size_before - size_after) / size_before, 2)
print(f" Fertig! ({input_pptx.name})") print(f"[OK] Fertig! ({input_pptx.name})")
print("📋 Zusammenfassung ----------------") print("Zusammenfassung ----------------")
print(" Vorher: ", human_mb(size_before), "MB") print(" Vorher: ", human_mb(size_before), "MB")
print(" Nachher: ", human_mb(size_after), "MB") print(" Nachher: ", human_mb(size_after), "MB")
print(" Ersparnis: ", f"{savings_pct}%") print(" Ersparnis: ", f"{savings_pct}%")
@@ -330,7 +374,7 @@ def main():
print("Threads used: ", args.threads," Threads") print("Threads used: ", args.threads," Threads")
if args.quality < 0 or args.quality > 100: if args.quality < 0 or args.quality > 100:
print(' Ungültige Qualität. Erlaubt: 0..100') print('[ERROR] Ungültige Qualität. Erlaubt: 0..100')
sys.exit(1) sys.exit(1)
input_files: list[Path] = [] input_files: list[Path] = []
@@ -346,11 +390,11 @@ def main():
batch_mode = len(input_files) > 1 batch_mode = len(input_files) > 1
if batch_mode and not args.output_dir: if batch_mode and not args.output_dir:
print(' Batch-Modus erkannt. Bitte -O/--output-dir angeben.') print('[ERROR] Batch-Modus erkannt. Bitte -O/--output-dir angeben.')
sys.exit(2) sys.exit(2)
if not which('caesiumclt'): if not which('caesiumclt'):
print(" 'caesiumclt' nicht gefunden. Bitte installieren und in PATH verfügbar machen.") print("[ERROR] 'caesiumclt' nicht gefunden. Bitte installieren und in PATH verfügbar machen.")
sys.exit(3) sys.exit(3)
overall_before = 0 overall_before = 0
@@ -361,7 +405,7 @@ def main():
if batch_mode: if batch_mode:
out_dir = Path(args.output_dir).resolve() out_dir = Path(args.output_dir).resolve()
out_dir.mkdir(parents=True, exist_ok=True) out_dir.mkdir(parents=True, exist_ok=True)
print(f"🗂️ Batch: {len(input_files)} Datei(en). Output-Verzeichnis: {out_dir}") print(f"Batch: {len(input_files)} Datei(en). Output-Verzeichnis: {out_dir}")
for src in input_files: for src in input_files:
if not src.exists(): if not src.exists():
print(f"- Übersprungen (nicht gefunden): {src}") print(f"- Übersprungen (nicht gefunden): {src}")
@@ -394,11 +438,11 @@ def main():
if batch_mode: if batch_mode:
print(f"====== 📊 Gesamt-Summary ======") print(f"====== Gesamt-Summary ======")
print(f" Dateien erfolgreich: {successes}") print(f"[SUCCESS] Dateien erfolgreich: {successes}")
if failures > 0: if failures > 0:
print(f"Dateien fehlgeschlagen: {failures}") print(f"[FAILED] Dateien fehlgeschlagen: {failures}")
if overall_before > 0: if overall_before > 0:
pct = round(100.0 * (overall_before - overall_after) / overall_before, 2) pct = round(100.0 * (overall_before - overall_after) / overall_before, 2)

View File

@@ -0,0 +1,142 @@
@echo off
setlocal EnableExtensions DisableDelayedExpansion
rem ==========================================================
rem PPTX Image Compressor - Drag&Drop Wrapper (robust + logging, RC-Fix)
rem ==========================================================
set "SELF_DIR=%~dp0"
set "RUNNER=%SELF_DIR%install_and_run.bat"
set "DEFAULT_THREADS=8"
set "DEFAULT_QUALITY=90"
set "PAUSE_ON_ERROR=1"
set "PAUSE_ALWAYS=1"
for /f "delims=" %%A in ('echo prompt $E^| cmd') do set "ESC=%%A"
set "GREEN=%ESC%[92m"
set "YELLOW=%ESC%[93m"
set "RED=%ESC%[91m"
set "RESET=%ESC%[0m"
if not exist "%RUNNER%" (
echo %RED%[ERROR]%RESET% Runner nicht gefunden: "%RUNNER%"
pause
exit /b 2
)
if "%~1"=="" (
echo Ziehe 1..n ^*.pptx Dateien auf "%~nx0".
pause
exit /b 64
)
set "LOGDIR=%SELF_DIR%logs"
if not exist "%LOGDIR%" mkdir "%LOGDIR%" >nul 2>&1
for /f "usebackq delims=" %%t in (`powershell -NoLogo -NoProfile -Command "(Get-Date).ToString('yyyy-MM-dd_HH-mm-ss')"`) do set "TS=%%t"
set "LOGFILE=%LOGDIR%\dragdrop_%TS%.log"
(
echo ==========================================================
echo Drag^&Drop Session %DATE% %TIME%
echo Runner: "%RUNNER%"
echo Wrapper: "%~nx0"
echo WorkingDir: "%CD%"
echo Defaults: threads=%DEFAULT_THREADS%, quality=%DEFAULT_QUALITY%
echo Args:
for %%# in (%*) do @echo "%%~f#"
echo ==========================================================
) >>"%LOGFILE%" 2>&1
set /a TOTAL=0, OK=0, FAIL=0, SKIP=0
:loop
if "%~1"=="" goto done
set "ARG_FULL=%~f1"
set "ARG_EXT=%~x1"
set /a TOTAL+=1
if not exist "%ARG_FULL%" (
echo %YELLOW%[SKIP]%RESET% Nicht gefunden: "%ARG_FULL%"
echo [SKIP] Not found: "%ARG_FULL%" >>"%LOGFILE%" 2>&1
set /a SKIP+=1
shift & goto loop
)
if exist "%ARG_FULL%\" (
echo %YELLOW%[SKIP]%RESET% Ist ein Ordner: "%ARG_FULL%"
echo [SKIP] Is a directory: "%ARG_FULL%" >>"%LOGFILE%" 2>&1
set /a SKIP+=1
shift & goto loop
)
if /I not "%ARG_EXT%"==".pptx" (
echo %YELLOW%[SKIP]%RESET% Keine PPTX: "%ARG_FULL%"
echo [SKIP] Not a .pptx: "%ARG_FULL%" >>"%LOGFILE%" 2>&1
set /a SKIP+=1
shift & goto loop
)
echo.
echo ===== Verarbeite: "%ARG_FULL%" =====
echo ----- Processing "%ARG_FULL%" ----- >>"%LOGFILE%" 2>&1
REM --- Runner aufrufen + vollständige Ausgabe loggen
call "%RUNNER%" -i "%ARG_FULL%" -t %DEFAULT_THREADS% -q %DEFAULT_QUALITY% >>"%LOGFILE%" 2>&1
echo ----- [INFO] Errorlevel = "%ERRORLEVEL%"
set "RC=%ERRORLEVEL%"
echo ----- [INFO] ReturnCode = "%RC%"
REM --- ROBUSTE NUMERISCHE PRÜFUNG STATT STRINGVERGLEICH
REM (GEQ 1 => Fehler; EQ 0 => OK)
if "%RC%"=="" set "RC=1"
set /a RC+=0
echo ----- [INFO] ReturnCodeAgain = "%RC%"
if %RC% GEQ 1 (
echo ----- [WARN] Assuming RC GEQ 1
echo %RED%[FAIL]%RESET% "%ARG_FULL%" (Code %RC%)
echo [FAIL] "%ARG_FULL%" Code=%RC% >>"%LOGFILE%" 2>&1
set /a FAIL+=1
) else (
echo %GREEN%[OK]%RESET% "%ARG_FULL%"
echo [OK] "%ARG_FULL%" >>"%LOGFILE%" 2>&1
set /a OK+=1
set /a FAIL=0
)
echo ---- [INFO] Fail-State = "%FAIL%"
shift
goto loop
:done
echo.
echo ------------------ Zusammenfassung ------------------
echo Dateien gesamt: %TOTAL%
echo Erfolgreich: %OK%
echo Fehlgeschlagen: %FAIL%
echo Uebersprungen: %SKIP%
echo Log-Datei: "%LOGFILE%"
echo ----------------------------------------------------
echo.>>"%LOGFILE%" & echo Summary: total=%TOTAL% ok=%OK% fail=%FAIL% skip=%SKIP%>>"%LOGFILE%"
if %FAIL% GTR 0 (
echo %RED%Ergebnis:%RESET% teils fehlgeschlagen. Bitte Log pruefen:
echo "%LOGFILE%"
if "%PAUSE_ON_ERROR%"=="1" (
echo.
echo [ENTER] druecken, um das Log in Notepad zu oeffnen...
pause >nul
start "" notepad "%LOGFILE%"
echo [CMD-Fenster bleibt bis zum Schliessen von Notepad geoeffnet.]
pause
)
endlocal & exit /b 1
) else (
echo %GREEN%Ergebnis:%RESET% alle erfolgreich.
if "%PAUSE_ALWAYS%"=="1" (
echo.
pause
)
endlocal & exit /b 0
)

View File

@@ -1 +0,0 @@
Place your PPTX files here for testing, or use -i with a full path.