update app

app/bluebeam_bci.py

@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+
+from pathlib import Path
+import argparse
+import pandas as pd
+
+BASE_DIR = Path(__file__).resolve().parents[1]
+DATA_DIR = BASE_DIR / "data"
+OUTPUT_DIR = BASE_DIR / "output"
+
+def clean_value(v):
+    if pd.isna(v):
+        return ""
+    return str(v).strip()
+
+def bci_escape(v):
+    v = clean_value(v)
+    v = v.replace("\\", "\\\\")
+    v = v.replace("'", "\\'")
+    v = v.replace("\n", "\\n")
+    return v
+
+def build_column_dict(row, exclude_cols):
+    data = {}
+    for col in row.index:
+        if col in exclude_cols:
+            continue
+        val = clean_value(row[col])
+        if val != "":
+            data[col] = val
+    return data
+
+def dict_to_bci_payload(d):
+    parts = []
+    for k, v in d.items():
+        parts.append(f"'{bci_escape(k)}':'{bci_escape(v)}'")
+    return "{" + ",".join(parts) + "}"
+
+def main():
+    parser = argparse.ArgumentParser(description="Generate Bluebeam BCI script from Markups CSV + update CSV.")
+    parser.add_argument("--bb-csv", default=str(DATA_DIR / "bluebeam_markups.csv"), help="Bluebeam Markups List CSV export")
+    parser.add_argument("--updates-csv", default=str(DATA_DIR / "bluebeam_updates.csv"), help="Your update CSV")
+    parser.add_argument("--out", default=str(OUTPUT_DIR / "update_columns.bci"), help="Output BCI file")
+    parser.add_argument("--pdf-path", default=r"C:\PATH\TO\TARGET.pdf", help="Windows path to target PDF for the BCI Open() command")
+    parser.add_argument("--match-column", default="Comment", help="Column in Bluebeam CSV to match against match_value")
+    parser.add_argument("--page-column", default="Page Index", help="Bluebeam page index column")
+    parser.add_argument("--id-column", default="ID", help="Bluebeam markup ID column")
+    parser.add_argument("--contains", action="store_true", help="Use contains match instead of exact match")
+    args = parser.parse_args()
+
+    bb_csv = Path(args.bb_csv)
+    updates_csv = Path(args.updates_csv)
+    out_path = Path(args.out)
+
+    OUTPUT_DIR.mkdir(exist_ok=True)
+
+    bb = pd.read_csv(bb_csv, dtype=str).fillna("")
+    upd = pd.read_csv(updates_csv, dtype=str).fillna("")
+
+    required_bb = {args.page_column, args.id_column, args.match_column}
+    missing_bb = required_bb - set(bb.columns)
+    if missing_bb:
+        raise ValueError(f"Bluebeam CSV missing required columns: {sorted(missing_bb)}")
+
+    required_upd = {"match_value"}
+    missing_upd = required_upd - set(upd.columns)
+    if missing_upd:
+        raise ValueError(f"Updates CSV missing required columns: {sorted(missing_upd)}")
+
+    lines = []
+    lines.append(f"Open('{args.pdf_path}', '')")
+
+    total_matches = 0
+
+    for _, urow in upd.iterrows():
+        match_value = clean_value(urow["match_value"])
+        if not match_value:
+            continue
+
+        if args.contains:
+            mask = bb[args.match_column].astype(str).str.contains(match_value, na=False, regex=False)
+        else:
+            mask = bb[args.match_column].astype(str).str.strip() == match_value
+
+        matches = bb[mask]
+
+        col_data = build_column_dict(urow, exclude_cols={"match_value"})
+        if not col_data:
+            continue
+
+        payload = dict_to_bci_payload(col_data)
+
+        for _, brow in matches.iterrows():
+            page_index = clean_value(brow[args.page_column])
+            markup_id = clean_value(brow[args.id_column])
+
+            if page_index == "" or markup_id == "":
+                continue
+
+            lines.append(f'ColumnDataSet({page_index},"{markup_id}","{payload}")')
+            total_matches += 1
+
+    lines.append("Save()")
+    lines.append("Close()")
+
+    out_path.write_text("\n".join(lines) + "\n", encoding="utf-8")
+
+    print(f"WROTE: {out_path}")
+    print(f"MATCHED MARKUPS: {total_matches}")
+
+if __name__ == "__main__":
+    main()

app/update_existing.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+
+from pathlib import Path
+import fitz
+
+BASE_DIR = Path(__file__).resolve().parents[1]
+INPUT = BASE_DIR / "input" / "okular_test.pdf"
+OUTPUT = BASE_DIR / "output" / "okular_test_updated.pdf"
+
+OLD_TEXT = "TITLE TEXT HERE"
+NEW_TEXT = "UPDATED TITLE TEXT\nLINE 2 UPDATED\nLINE 3 UPDATED"
+
+doc = fitz.open(INPUT)
+
+changed = 0
+
+for page in doc:
+    for annot in page.annots() or []:
+        info = annot.info or {}
+        content = info.get("content", "")
+
+        if OLD_TEXT in content:
+            info["content"] = NEW_TEXT
+            annot.set_info(info)
+
+            # FreeText annotations need appearance regenerated
+            if annot.type[1] == "FreeText":
+                annot.update()
+
+            changed += 1
+
+doc.save(OUTPUT, garbage=4, deflate=True)
+doc.close()
+
+print(f"Updated {changed} annotation(s)")
+print(f"Wrote {OUTPUT}")