plcode-darwin-x64-baseline 2.1.0

package/.plcode/skill/experimental/document-xlsx/recalc.py

@@ -0,0 +1,211 @@
+#!/usr/bin/env python3
+"""
+Excel Formula Recalculation Script
+Recalculates all formulas in an Excel file using LibreOffice
+"""
+
+import json
+import sys
+import subprocess
+import os
+import platform
+from pathlib import Path
+from openpyxl import load_workbook
+
+
+def setup_libreoffice_macro():
+    """Setup LibreOffice macro for recalculation if not already configured"""
+    if platform.system() == "Darwin":
+        macro_dir = os.path.expanduser(
+            "~/Library/Application Support/LibreOffice/4/user/basic/Standard"
+        )
+    elif platform.system() == "Windows":
+        macro_dir = os.path.join(
+            os.environ.get("APPDATA", ""),
+            "LibreOffice",
+            "4",
+            "user",
+            "basic",
+            "Standard",
+        )
+    else:
+        macro_dir = os.path.expanduser("~/.config/libreoffice/4/user/basic/Standard")
+
+    macro_file = os.path.join(macro_dir, "Module1.xba")
+
+    if os.path.exists(macro_file):
+        with open(macro_file, "r") as f:
+            if "RecalculateAndSave" in f.read():
+                return True
+
+    if not os.path.exists(macro_dir):
+        subprocess.run(
+            ["soffice", "--headless", "--terminate_after_init"],
+            capture_output=True,
+            timeout=10,
+        )
+        os.makedirs(macro_dir, exist_ok=True)
+
+    macro_content = """<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE script:module PUBLIC "-//OpenOffice.org//DTD OfficeDocument 1.0//EN" "module.dtd">
+<script:module xmlns:script="http://openoffice.org/2000/script" script:name="Module1" script:language="StarBasic">
+    Sub RecalculateAndSave()
+      ThisComponent.calculateAll()
+      ThisComponent.store()
+      ThisComponent.close(True)
+    End Sub
+</script:module>"""
+
+    try:
+        with open(macro_file, "w") as f:
+            f.write(macro_content)
+        return True
+    except Exception:
+        return False
+
+
+def recalc(filename, timeout=30):
+    """
+    Recalculate formulas in Excel file and report any errors
+
+    Args:
+        filename: Path to Excel file
+        timeout: Maximum time to wait for recalculation (seconds)
+
+    Returns:
+        dict with error locations and counts
+    """
+    if not Path(filename).exists():
+        return {"error": f"File {filename} does not exist"}
+
+    abs_path = str(Path(filename).absolute())
+
+    if not setup_libreoffice_macro():
+        return {"error": "Failed to setup LibreOffice macro"}
+
+    cmd = [
+        "soffice",
+        "--headless",
+        "--norestore",
+        "vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application",
+        abs_path,
+    ]
+
+    # Handle timeout command differences between Linux and macOS
+    if platform.system() != "Windows":
+        timeout_cmd = "timeout" if platform.system() == "Linux" else None
+        if platform.system() == "Darwin":
+            # Check if gtimeout is available on macOS
+            try:
+                subprocess.run(
+                    ["gtimeout", "--version"],
+                    capture_output=True,
+                    timeout=1,
+                    check=False,
+                )
+                timeout_cmd = "gtimeout"
+            except (FileNotFoundError, subprocess.TimeoutExpired):
+                pass
+
+        if timeout_cmd:
+            cmd = [timeout_cmd, str(timeout)] + cmd
+
+    result = subprocess.run(cmd, capture_output=True, text=True)
+
+    if result.returncode != 0 and result.returncode != 124:  # 124 is timeout exit code
+        error_msg = result.stderr or "Unknown error during recalculation"
+        if "Module1" in error_msg or "RecalculateAndSave" not in error_msg:
+            return {"error": "LibreOffice macro not configured properly"}
+        else:
+            return {"error": error_msg}
+
+    # Check for Excel errors in the recalculated file - scan ALL cells
+    try:
+        wb = load_workbook(filename, data_only=True)
+
+        excel_errors = [
+            "#VALUE!",
+            "#DIV/0!",
+            "#REF!",
+            "#NAME?",
+            "#NULL!",
+            "#NUM!",
+            "#N/A",
+        ]
+        error_details = {err: [] for err in excel_errors}
+        total_errors = 0
+
+        for sheet_name in wb.sheetnames:
+            ws = wb[sheet_name]
+            # Check ALL rows and columns - no limits
+            for row in ws.iter_rows():
+                for cell in row:
+                    if cell.value is not None and isinstance(cell.value, str):
+                        for err in excel_errors:
+                            if err in cell.value:
+                                location = f"{sheet_name}!{cell.coordinate}"
+                                error_details[err].append(location)
+                                total_errors += 1
+                                break
+
+        wb.close()
+
+        # Build result summary
+        result = {
+            "status": "success" if total_errors == 0 else "errors_found",
+            "total_errors": total_errors,
+            "error_summary": {},
+        }
+
+        # Add non-empty error categories
+        for err_type, locations in error_details.items():
+            if locations:
+                result["error_summary"][err_type] = {
+                    "count": len(locations),
+                    "locations": locations[:20],  # Show up to 20 locations
+                }
+
+        # Add formula count for context - also check ALL cells
+        wb_formulas = load_workbook(filename, data_only=False)
+        formula_count = 0
+        for sheet_name in wb_formulas.sheetnames:
+            ws = wb_formulas[sheet_name]
+            for row in ws.iter_rows():
+                for cell in row:
+                    if (
+                        cell.value
+                        and isinstance(cell.value, str)
+                        and cell.value.startswith("=")
+                    ):
+                        formula_count += 1
+        wb_formulas.close()
+
+        result["total_formulas"] = formula_count
+
+        return result
+
+    except Exception as e:
+        return {"error": str(e)}
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python recalc.py <excel_file> [timeout_seconds]")
+        print("\nRecalculates all formulas in an Excel file using LibreOffice")
+        print("\nReturns JSON with error details:")
+        print("  - status: 'success' or 'errors_found'")
+        print("  - total_errors: Total number of Excel errors found")
+        print("  - total_formulas: Number of formulas in the file")
+        print("  - error_summary: Breakdown by error type with locations")
+        print("    - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A")
+        sys.exit(1)
+
+    filename = sys.argv[1]
+    timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30
+
+    result = recalc(filename, timeout)
+    print(json.dumps(result, indent=2))
+
+
+if __name__ == "__main__":
+    main()

package/.plcode/skill/experimental/document-xlsx/scripts/office/helpers/merge_runs.py

@@ -0,0 +1,199 @@
+"""Merge adjacent runs with identical formatting in DOCX.
+
+Merges adjacent <w:r> elements that have identical <w:rPr> properties.
+Works on runs in paragraphs and inside tracked changes (<w:ins>, <w:del>).
+
+Also:
+- Removes rsid attributes from runs (revision metadata that doesn't affect rendering)
+- Removes proofErr elements (spell/grammar markers that block merging)
+"""
+
+from pathlib import Path
+
+import defusedxml.minidom
+
+
+def merge_runs(input_dir: str) -> tuple[int, str]:
+    doc_xml = Path(input_dir) / "word" / "document.xml"
+
+    if not doc_xml.exists():
+        return 0, f"Error: {doc_xml} not found"
+
+    try:
+        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
+        root = dom.documentElement
+
+        _remove_elements(root, "proofErr")
+        _strip_run_rsid_attrs(root)
+
+        containers = {run.parentNode for run in _find_elements(root, "r")}
+
+        merge_count = 0
+        for container in containers:
+            merge_count += _merge_runs_in(container)
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Merged {merge_count} runs"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+
+
+def _find_elements(root, tag: str) -> list:
+    results = []
+
+    def traverse(node):
+        if node.nodeType == node.ELEMENT_NODE:
+            name = node.localName or node.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(node)
+            for child in node.childNodes:
+                traverse(child)
+
+    traverse(root)
+    return results
+
+
+def _get_child(parent, tag: str):
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                return child
+    return None
+
+
+def _get_children(parent, tag: str) -> list:
+    results = []
+    for child in parent.childNodes:
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(child)
+    return results
+
+
+def _is_adjacent(elem1, elem2) -> bool:
+    node = elem1.nextSibling
+    while node:
+        if node == elem2:
+            return True
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+    return False
+
+
+
+
+def _remove_elements(root, tag: str):
+    for elem in _find_elements(root, tag):
+        if elem.parentNode:
+            elem.parentNode.removeChild(elem)
+
+
+def _strip_run_rsid_attrs(root):
+    for run in _find_elements(root, "r"):
+        for attr in list(run.attributes.values()):
+            if "rsid" in attr.name.lower():
+                run.removeAttribute(attr.name)
+
+
+
+
+def _merge_runs_in(container) -> int:
+    merge_count = 0
+    run = _first_child_run(container)
+
+    while run:
+        while True:
+            next_elem = _next_element_sibling(run)
+            if next_elem and _is_run(next_elem) and _can_merge(run, next_elem):
+                _merge_run_content(run, next_elem)
+                container.removeChild(next_elem)
+                merge_count += 1
+            else:
+                break
+
+        _consolidate_text(run)
+        run = _next_sibling_run(run)
+
+    return merge_count
+
+
+def _first_child_run(container):
+    for child in container.childNodes:
+        if child.nodeType == child.ELEMENT_NODE and _is_run(child):
+            return child
+    return None
+
+
+def _next_element_sibling(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _next_sibling_run(node):
+    sibling = node.nextSibling
+    while sibling:
+        if sibling.nodeType == sibling.ELEMENT_NODE:
+            if _is_run(sibling):
+                return sibling
+        sibling = sibling.nextSibling
+    return None
+
+
+def _is_run(node) -> bool:
+    name = node.localName or node.tagName
+    return name == "r" or name.endswith(":r")
+
+
+def _can_merge(run1, run2) -> bool:
+    rpr1 = _get_child(run1, "rPr")
+    rpr2 = _get_child(run2, "rPr")
+
+    if (rpr1 is None) != (rpr2 is None):
+        return False
+    if rpr1 is None:
+        return True
+    return rpr1.toxml() == rpr2.toxml()  
+
+
+def _merge_run_content(target, source):
+    for child in list(source.childNodes):
+        if child.nodeType == child.ELEMENT_NODE:
+            name = child.localName or child.tagName
+            if name != "rPr" and not name.endswith(":rPr"):
+                target.appendChild(child)
+
+
+def _consolidate_text(run):
+    t_elements = _get_children(run, "t")
+
+    for i in range(len(t_elements) - 1, 0, -1):
+        curr, prev = t_elements[i], t_elements[i - 1]
+
+        if _is_adjacent(prev, curr):
+            prev_text = prev.firstChild.data if prev.firstChild else ""
+            curr_text = curr.firstChild.data if curr.firstChild else ""
+            merged = prev_text + curr_text
+
+            if prev.firstChild:
+                prev.firstChild.data = merged
+            else:
+                prev.appendChild(run.ownerDocument.createTextNode(merged))
+
+            if merged.startswith(" ") or merged.endswith(" "):
+                prev.setAttribute("xml:space", "preserve")
+            elif prev.hasAttribute("xml:space"):
+                prev.removeAttribute("xml:space")
+
+            run.removeChild(curr)

package/.plcode/skill/experimental/document-xlsx/scripts/office/helpers/simplify_redlines.py

@@ -0,0 +1,197 @@
+"""Simplify tracked changes by merging adjacent w:ins or w:del elements.
+
+Merges adjacent <w:ins> elements from the same author into a single element.
+Same for <w:del> elements. This makes heavily-redlined documents easier to
+work with by reducing the number of tracked change wrappers.
+
+Rules:
+- Only merges w:ins with w:ins, w:del with w:del (same element type)
+- Only merges if same author (ignores timestamp differences)
+- Only merges if truly adjacent (only whitespace between them)
+"""
+
+import xml.etree.ElementTree as ET
+import zipfile
+from pathlib import Path
+
+import defusedxml.minidom
+
+WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
+
+
+def simplify_redlines(input_dir: str) -> tuple[int, str]:
+    doc_xml = Path(input_dir) / "word" / "document.xml"
+
+    if not doc_xml.exists():
+        return 0, f"Error: {doc_xml} not found"
+
+    try:
+        dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8"))
+        root = dom.documentElement
+
+        merge_count = 0
+
+        containers = _find_elements(root, "p") + _find_elements(root, "tc")
+
+        for container in containers:
+            merge_count += _merge_tracked_changes_in(container, "ins")
+            merge_count += _merge_tracked_changes_in(container, "del")
+
+        doc_xml.write_bytes(dom.toxml(encoding="UTF-8"))
+        return merge_count, f"Simplified {merge_count} tracked changes"
+
+    except Exception as e:
+        return 0, f"Error: {e}"
+
+
+def _merge_tracked_changes_in(container, tag: str) -> int:
+    merge_count = 0
+
+    tracked = [
+        child
+        for child in container.childNodes
+        if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag)
+    ]
+
+    if len(tracked) < 2:
+        return 0
+
+    i = 0
+    while i < len(tracked) - 1:
+        curr = tracked[i]
+        next_elem = tracked[i + 1]
+
+        if _can_merge_tracked(curr, next_elem):
+            _merge_tracked_content(curr, next_elem)
+            container.removeChild(next_elem)
+            tracked.pop(i + 1)
+            merge_count += 1
+        else:
+            i += 1
+
+    return merge_count
+
+
+def _is_element(node, tag: str) -> bool:
+    name = node.localName or node.tagName
+    return name == tag or name.endswith(f":{tag}")
+
+
+def _get_author(elem) -> str:
+    author = elem.getAttribute("w:author")
+    if not author:
+        for attr in elem.attributes.values():
+            if attr.localName == "author" or attr.name.endswith(":author"):
+                return attr.value
+    return author
+
+
+def _can_merge_tracked(elem1, elem2) -> bool:
+    if _get_author(elem1) != _get_author(elem2):
+        return False
+
+    node = elem1.nextSibling
+    while node and node != elem2:
+        if node.nodeType == node.ELEMENT_NODE:
+            return False
+        if node.nodeType == node.TEXT_NODE and node.data.strip():
+            return False
+        node = node.nextSibling
+
+    return True
+
+
+def _merge_tracked_content(target, source):
+    while source.firstChild:
+        child = source.firstChild
+        source.removeChild(child)
+        target.appendChild(child)
+
+
+def _find_elements(root, tag: str) -> list:
+    results = []
+
+    def traverse(node):
+        if node.nodeType == node.ELEMENT_NODE:
+            name = node.localName or node.tagName
+            if name == tag or name.endswith(f":{tag}"):
+                results.append(node)
+            for child in node.childNodes:
+                traverse(child)
+
+    traverse(root)
+    return results
+
+
+def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]:
+    if not doc_xml_path.exists():
+        return {}
+
+    try:
+        tree = ET.parse(doc_xml_path)
+        root = tree.getroot()
+    except ET.ParseError:
+        return {}
+
+    namespaces = {"w": WORD_NS}
+    author_attr = f"{{{WORD_NS}}}author"
+
+    authors: dict[str, int] = {}
+    for tag in ["ins", "del"]:
+        for elem in root.findall(f".//w:{tag}", namespaces):
+            author = elem.get(author_attr)
+            if author:
+                authors[author] = authors.get(author, 0) + 1
+
+    return authors
+
+
+def _get_authors_from_docx(docx_path: Path) -> dict[str, int]:
+    try:
+        with zipfile.ZipFile(docx_path, "r") as zf:
+            if "word/document.xml" not in zf.namelist():
+                return {}
+            with zf.open("word/document.xml") as f:
+                tree = ET.parse(f)
+                root = tree.getroot()
+
+                namespaces = {"w": WORD_NS}
+                author_attr = f"{{{WORD_NS}}}author"
+
+                authors: dict[str, int] = {}
+                for tag in ["ins", "del"]:
+                    for elem in root.findall(f".//w:{tag}", namespaces):
+                        author = elem.get(author_attr)
+                        if author:
+                            authors[author] = authors.get(author, 0) + 1
+                return authors
+    except (zipfile.BadZipFile, ET.ParseError):
+        return {}
+
+
+def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str:
+    modified_xml = modified_dir / "word" / "document.xml"
+    modified_authors = get_tracked_change_authors(modified_xml)
+
+    if not modified_authors:
+        return default
+
+    original_authors = _get_authors_from_docx(original_docx)
+
+    new_changes: dict[str, int] = {}
+    for author, count in modified_authors.items():
+        original_count = original_authors.get(author, 0)
+        diff = count - original_count
+        if diff > 0:
+            new_changes[author] = diff
+
+    if not new_changes:
+        return default
+
+    if len(new_changes) == 1:
+        return next(iter(new_changes))
+
+    raise ValueError(
+        f"Multiple authors added new changes: {new_changes}. "
+        "Cannot infer which author to validate."
+    )