Bulk edit

Format N paragraphs / replace across M files

Ported from nbs/01_tutorials/05_usecase_bulk_edit.ipynb.

1. Apply a style to every heading paragraph

from hwpapi import App
from hwpapi.low.parametersets import CharShape

with App() as app:
    app.open("document.hwp")

    headings = app.doc.paragraphs.filter(lambda p: p.style.startswith("제목"))
    print(f"Found {len(headings)} headings")

    shape = CharShape(Bold=True, TextColor="#1F4E79")
    for h in headings:
        h.charshape = shape

    app.save()

2. Replace a phrase across every .hwp in a folder

from pathlib import Path
from hwpapi import App


def replace_across(folder: Path, find: str, replace: str):
    with App(is_visible=False) as app:
        for hwp in sorted(folder.glob("*.hwp")):
            app.open(str(hwp))
            count = app.doc.replace_all(find, replace)
            if count:
                app.save()
                print(f"{hwp.name}: {count} replacements")
            app.close()


replace_across(Path("reports"), "FY2025", "FY2026")

3. Batch-apply a charshape with undo grouping

HWP’s undo stack is per-document; wrapping a loop in an undo-group lets the user press Ctrl+Z once to revert the whole batch:

from hwpapi import App
from hwpapi.context import charshape_scope

with App() as app:
    app.open("document.hwp")

    # Every sub-edit collapses into a single undo entry
    with app.doc.scan() as scope:
        for p in app.doc.paragraphs:
            if "DRAFT" in p.text:
                with charshape_scope(app, color="#E74C3C", bold=True):
                    app.doc.select_text(p.start, p.end)
                    # re-apply the scope's shape to the selection
                    app.actions.CharShape.run()

    app.save()

4. Aggregate statistics

from collections import Counter
from hwpapi import App

with App() as app:
    app.open("document.hwp")

    styles = Counter(p.style for p in app.doc.paragraphs)
    print("Most common styles:")
    for style, n in styles.most_common(10):
        print(f"  {n:5d}  {style}")

    word_count = sum(len(p.text.split()) for p in app.doc.paragraphs)
    print(f"\nTotal words: {word_count}")

Performance tips

  • Hide HWP — App(is_visible=False) avoids window-flash overhead.
  • Iterate, don’t index — for p in app.doc.paragraphs is cheaper than for i in range(len(app.doc.paragraphs)): app.doc.paragraphs[i] because the collection can stream without re-resolving.
  • Batch saves — save once per file, not per paragraph.
  • Read-only vs. write — reading 10 k paragraphs is ~1 s; writing 10 k paragraphs is 10× that. Filter first, then write only what changed.

See also

Back to top