Initial toolkit: scripts, references, skills, and term database

2026-07-10 21:01:02 +08:00
commit ac9e6e3d1f
51 changed files with 5192 additions and 0 deletions
@@ -0,0 +1,68 @@
+import sys, yaml
+from pptx import Presentation
+from pptx.util import Pt
+from pptx.enum.text import MSO_AUTO_SIZE
+
+FONT_SCALE = 0.82  # shrink ~18%
+
+yaml_path, src_path, out_path = sys.argv[1], sys.argv[2], sys.argv[3]
+
+with open(yaml_path) as f:
+    entries = yaml.safe_load(f)
+
+index = {}
+for e in entries:
+    index[(e["slide"], e["shape"], e["run"])] = e["en"]
+
+
+def shrink_font_tf(tf):
+    for para in tf.paragraphs:
+        for run in para.runs:
+            if run.font.size:
+                run.font.size = Pt(int(run.font.size.pt * FONT_SCALE))
+    try:
+        tf.auto_size = MSO_AUTO_SIZE.TEXT_TO_FIT_SHAPE
+    except Exception:
+        pass
+
+
+prs = Presentation(src_path)
+
+for slide_num, slide in enumerate(prs.slides, 1):
+    for shape_idx, shape in enumerate(slide.shapes):
+        if shape.has_text_frame:
+            has_translation = False
+            for para_idx, para in enumerate(shape.text_frame.paragraphs):
+                key = (slide_num, shape_idx, para_idx)
+                if key in index:
+                    has_translation = True
+                    en = index[key]
+                    for r in para.runs:
+                        r.text = ""
+                    if para.runs:
+                        para.runs[0].text = en
+                    else:
+                        para.add_run().text = en
+            if has_translation:
+                shrink_font_tf(shape.text_frame)
+
+        elif shape.has_table:
+            num_rows = len(shape.table.rows)
+            for r in range(num_rows * len(shape.table.columns)):
+                key = (slide_num, shape_idx, r)
+                if key in index:
+                    row = r % num_rows
+                    col = r // num_rows
+                    shape.table.cell(row, col).text = index[key]
+            for row in shape.table.rows:
+                for cell in row.cells:
+                    shrink_font_tf(cell.text_frame)
+
+    key = (slide_num, -1, 0)
+    if key in index and slide.has_notes_slide:
+        ns = slide.notes_slide
+        ns.notes_text_frame.clear()
+        ns.notes_text_frame.paragraphs[0].add_run().text = index[key]
+
+prs.save(out_path)
+print(f"Saved {out_path}")
@@ -0,0 +1,68 @@
+import sys, yaml
+from pptx import Presentation
+
+PLACEHOLDER_KINDS = {
+    1: "title", 2: "body", 3: "center_title",
+    4: "subtitle", 5: "body", 6: "body", 7: "body",
+}
+
+
+def shape_kind(shape):
+    if shape.has_table:
+        return "table"
+    try:
+        ph = shape.placeholder_format
+        if ph is not None and ph.type is not None:
+            return PLACEHOLDER_KINDS.get(ph.type, "body")
+    except ValueError:
+        pass
+    return "body"
+
+
+def extract(pptx_path):
+    prs = Presentation(pptx_path)
+    entries = []
+
+    for slide_num, slide in enumerate(prs.slides, 1):
+        for shape_idx, shape in enumerate(slide.shapes):
+            kind = shape_kind(shape)
+
+            if shape.has_text_frame:
+                for para_idx, para in enumerate(shape.text_frame.paragraphs):
+                    full = para.text.strip()
+                    if not full:
+                        continue
+                    entries.append({
+                        "slide": slide_num, "shape": shape_idx,
+                        "run": para_idx, "kind": kind,
+                        "zh": full, "en": "",
+                    })
+
+            elif shape.has_table:
+                for row_idx, row in enumerate(shape.table.rows):
+                    for col_idx, cell in enumerate(row.cells):
+                        text = cell.text.strip()
+                        if not text:
+                            continue
+                        entries.append({
+                            "slide": slide_num, "shape": shape_idx,
+                            "run": len(shape.table.rows) * col_idx + row_idx,
+                            "kind": "table", "zh": text, "en": "",
+                        })
+
+        if slide.has_notes_slide:
+            notes = slide.notes_slide.notes_text_frame.text.strip()
+            if notes:
+                entries.append({
+                    "slide": slide_num, "shape": -1, "run": 0,
+                    "kind": "notes", "zh": notes, "en": "",
+                })
+
+    return entries
+
+
+if __name__ == "__main__":
+    entries = extract(sys.argv[1])
+    with open(sys.argv[2], "w") as f:
+        yaml.dump(entries, f, allow_unicode=True, default_flow_style=False, sort_keys=False)
+    print(f"Extracted {len(entries)} entries to {sys.argv[2]}")