Initial commit: lesson-highlights generator

temp/check_log.py

@@ -0,0 +1,9 @@
+f = open(r'D:\F\NewI\opencode\daily-workspace\temp\cli_run_log.txt', 'rb')
+data = f.read()
+f.close()
+
+print('Total bytes:', len(data))
+print('First 300 hex:', data[:300].hex())
+print()
+print('UTF-8 decode of first 300:')
+print(data[:300].decode('utf-8', 'replace'))

temp/check_pptx.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" -c "import pptx; print('pptx available')"

temp/check_pptx2.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\check_pptx2.py"

temp/check_pptx2.py

@@ -0,0 +1,10 @@
+import sys
+out = r"D:\F\NewI\opencode\daily-workspace\temp\check_pptx_out.txt"
+try:
+    import pptx
+    result = "pptx available: " + pptx.__version__
+except ImportError as e:
+    result = "pptx NOT available: " + str(e)
+with open(out, "w", encoding="utf-8") as f:
+    f.write(result)
+print(result)

temp/check_transcript.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\check_transcript.py"

temp/check_transcript.py

@@ -0,0 +1,17 @@
+import os
+import json
+
+inter_dir = r"D:\F\NewI\opencode\daily-workspace\projects\piano-lesson-highlights\cases\lesson1\output_cli_full\intermediates"
+transcript_file = os.path.join(inter_dir, "full_transcript.json")
+
+if os.path.exists(transcript_file):
+    size = os.path.getsize(transcript_file)
+    with open(transcript_file, "r", encoding="utf-8") as f:
+        data = json.load(f)
+    print(f"Transcript exists: {size} bytes")
+    print(f"Segments: {len(data)}")
+    if data:
+        print(f"First segment: {data[0]}")
+        print(f"Last segment: {data[-1]}")
+else:
+    print("Transcript file NOT found")

temp/debug_ppt.bat

@@ -0,0 +1,4 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\debug_ppt.py"
+pause

temp/debug_ppt.py

@@ -0,0 +1,30 @@
+import zipfile
+import re
+
+ppt = r"D:\F\yc\课程上架\福田商圈夜校\课程视频\钢琴演奏入门第一课.pptx"
+
+with zipfile.ZipFile(ppt, "r") as z:
+    names = z.namelist()
+    slide_files = [f for f in names if f.startswith("ppt/slides/slide") and f.endswith(".xml")]
+    print(f"Total files in zip: {len(names)}")
+    print(f"Slide files found: {len(slide_files)}")
+    print(f"First 5 slide files: {slide_files[:5]}")
+
+    # Test presentation.xml
+    try:
+        pres_xml = z.read("ppt/presentation.xml").decode("utf-8", errors="replace")
+        sld_ids = re.findall(r'<p:sldId\b[^>]*r:id="([^"]+)"', pres_xml)
+        print(f"\nsldIdList rIds: {sld_ids[:5]}")
+    except Exception as e:
+        print(f"\npresentation.xml error: {e}")
+
+    # Test rels
+    try:
+        rels_xml = z.read("ppt/_rels/presentation.xml.rels").decode("utf-8", errors="replace")
+        rid_to_target = dict(re.findall(r'Id="([^"]+)"[^>]*Target="([^"]+)"', rels_xml))
+        print(f"Rels entries: {len(rid_to_target)}")
+        # Show a sample
+        for k, v in list(rid_to_target.items())[:3]:
+            print(f"  {k} -> {v}")
+    except Exception as e:
+        print(f"\nrels error: {e}")

temp/debug_ppt2.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\debug_ppt2.py"

temp/debug_ppt2.py

@@ -0,0 +1,34 @@
+import zipfile, re, sys
+
+ppt = r"D:\F\yc\课程上架\福田商圈夜校\课程视频\钢琴演奏入门第一课.pptx"
+out = r"D:\F\NewI\opencode\daily-workspace\temp\debug_ppt_out.txt"
+
+results = []
+
+with zipfile.ZipFile(ppt, "r") as z:
+    names = z.namelist()
+    slide_files = [f for f in names if f.startswith("ppt/slides/slide") and f.endswith(".xml")]
+    results.append(f"Total files in zip: {len(names)}")
+    results.append(f"Slide files found: {len(slide_files)}")
+    results.append(f"First 5: {slide_files[:5]}")
+
+    try:
+        pres_xml = z.read("ppt/presentation.xml").decode("utf-8", errors="replace")
+        sld_ids = re.findall(r'<p:sldId\b[^>]*r:id="([^"]+)"', pres_xml)
+        results.append(f"sldIds: {sld_ids[:5]}")
+    except Exception as e:
+        results.append(f"pres error: {e}")
+
+    try:
+        rels_xml = z.read("ppt/_rels/presentation.xml.rels").decode("utf-8", errors="replace")
+        rid_to_target = dict(re.findall(r'Id="([^"]+)"[^>]*Target="([^"]+)"', rels_xml))
+        results.append(f"rels count: {len(rid_to_target)}")
+        for k, v in list(rid_to_target.items())[:3]:
+            results.append(f"  {k} -> {v}")
+    except Exception as e:
+        results.append(f"rels error: {e}")
+
+with open(out, "w", encoding="utf-8") as f:
+    f.write("\n".join(results))
+
+print("Done, see", out)

temp/debug_slide1.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\debug_slide1.py" > "D:\F\NewI\opencode\daily-workspace\temp\debug_slide1_out.txt" 2>&1

temp/debug_slide1.py

@@ -0,0 +1,23 @@
+import zipfile, re, os
+
+ppt = r"D:\F\yc\课程上架\福田商圈夜校\课程视频\钢琴演奏入门第一课.pptx"
+out_dir = r"D:\F\NewI\opencode\daily-workspace\temp"
+slide1_out = os.path.join(out_dir, "slide1_texts.txt")
+xml_out = os.path.join(out_dir, "slide1_xml_preview.txt")
+
+with zipfile.ZipFile(ppt, "r") as z:
+    slide1_file = "ppt/slides/slide1.xml"
+    content = z.read(slide1_file).decode("utf-8", errors="replace")
+    all_texts = re.findall(r"<a:t[^>]*>([^<]*)</a:t>", content)
+
+    meaningful = [t for t in all_texts if t.strip()]
+    with open(slide1_out, "w", encoding="utf-8") as f:
+        f.write(f"Total fragments: {len(all_texts)}\n")
+        f.write(f"Meaningful fragments: {len(meaningful)}\n\n")
+        for i, t in enumerate(meaningful):
+            f.write(f"[{i}] {t}\n")
+
+    with open(xml_out, "w", encoding="utf-8") as f:
+        f.write(content[:8000])
+
+print("Done")

temp/do_install.bat

@@ -0,0 +1,3 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" "D:\F\NewI\opencode\daily-workspace\projects\piano-highlight-app\temp\do_install.py"

temp/do_install.py

@@ -0,0 +1,12 @@
+import subprocess
+import sys
+
+venv_python = r"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe"
+result = subprocess.run(
+    [venv_python, "-m", "pip", "install", "python-pptx"],
+    capture_output=True,
+    text=True
+)
+print("STDOUT:", result.stdout)
+print("STDERR:", result.stderr)
+print("Return code:", result.returncode)

temp/install_pptx.bat

@@ -0,0 +1,6 @@
+@echo off
+chcp 65001 >nul
+echo Installing python-pptx...
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" -m pip install python-pptx -q
+echo Done
+pause

temp/install_pptx2.bat

@@ -0,0 +1,4 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" -m pip install python-pptx
+echo Exit: %errorlevel%

temp/install_pptx3.bat

@@ -0,0 +1,4 @@
+@echo off
+chcp 65001 >nul
+"D:\ProgramData\anaconda3\envs\py312_cuda\python.exe" -m pip install python-pptx > "D:\F\NewI\opencode\daily-workspace\temp\pip_out.txt" 2>&1
+echo Exit: %errorlevel%

temp/kill_python.ps1

@@ -0,0 +1,12 @@
+# Kill all python processes related to our CLI
+Get-Process python -ErrorAction SilentlyContinue | Stop-Process -Force
+Start-Sleep 3
+
+# Verify killed
+$remaining = Get-Process python -ErrorAction SilentlyContinue
+if ($remaining) {
+    Write-Host "Still running:"
+    $remaining | ForEach-Object { Write-Host "  PID:" $_.Id }
+} else {
+    Write-Host "All python processes killed"
+}

temp/read_log.py

@@ -0,0 +1,5 @@
+f = open(r'D:\F\NewI\opencode\daily-workspace\temp\cli_run_log.txt', 'r', encoding='utf-8')
+lines = f.readlines()
+f.close()
+for l in lines[:35]:
+    print(l.rstrip())