sophhub 0.4.19 → 0.4.21

package/skills/sophnet-docx/src/scripts/ensure_uv_env.sh

@@ -1,68 +1,68 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-SKILL_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
-VENV_PYTHON="$SKILL_DIR/.venv/bin/python"
-QUIET=false
-FORCE_SYNC=false
-
-usage() {
-  cat <<'USAGE'
-Usage:
-  bash ensure_uv_env.sh [options]
-
-Options:
-  --quiet        Reduce non-error output.
-  --force-sync   Force uv sync even when .venv already exists.
-USAGE
-}
-
-log() {
-  if [[ "$QUIET" != true ]]; then
-    echo "$1" >&2
-  fi
-}
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --quiet)
-      QUIET=true
-      shift
-      ;;
-    --force-sync)
-      FORCE_SYNC=true
-      shift
-      ;;
-    -h|--help)
-      usage
-      exit 0
-      ;;
-    *)
-      echo "Unknown argument: $1" >&2
-      usage
-      exit 1
-      ;;
-  esac
-done
-
-if ! command -v uv >/dev/null 2>&1; then
-  echo "Error: uv is required but not found." >&2
-  echo "Install uv first: https://docs.astral.sh/uv/getting-started/installation/" >&2
-  exit 1
-fi
-
-need_sync=false
-
-if [[ "$FORCE_SYNC" == true || ! -x "$VENV_PYTHON" ]]; then
-  need_sync=true
-elif ! "$VENV_PYTHON" -c 'import defusedxml.minidom, lxml.etree' >/dev/null 2>&1; then
-  need_sync=true
-fi
-
-if [[ "$need_sync" == true ]]; then
-  log "Syncing uv environment at $SKILL_DIR/.venv"
-  uv sync --project "$SKILL_DIR" --no-dev
-else
-  log "uv environment already ready: $SKILL_DIR/.venv"
-fi
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+SKILL_DIR="$(cd "$SCRIPT_DIR/.." && pwd)"
+VENV_PYTHON="$SKILL_DIR/.venv/bin/python"
+QUIET=false
+FORCE_SYNC=false
+
+usage() {
+  cat <<'USAGE'
+Usage:
+  bash ensure_uv_env.sh [options]
+
+Options:
+  --quiet        Reduce non-error output.
+  --force-sync   Force uv sync even when .venv already exists.
+USAGE
+}
+
+log() {
+  if [[ "$QUIET" != true ]]; then
+    echo "$1" >&2
+  fi
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --quiet)
+      QUIET=true
+      shift
+      ;;
+    --force-sync)
+      FORCE_SYNC=true
+      shift
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage
+      exit 1
+      ;;
+  esac
+done
+
+if ! command -v uv >/dev/null 2>&1; then
+  echo "Error: uv is required but not found." >&2
+  echo "Install uv first: https://docs.astral.sh/uv/getting-started/installation/" >&2
+  exit 1
+fi
+
+need_sync=false
+
+if [[ "$FORCE_SYNC" == true || ! -x "$VENV_PYTHON" ]]; then
+  need_sync=true
+elif ! "$VENV_PYTHON" -c 'import defusedxml.minidom, lxml.etree' >/dev/null 2>&1; then
+  need_sync=true
+fi
+
+if [[ "$need_sync" == true ]]; then
+  log "Syncing uv environment at $SKILL_DIR/.venv"
+  uv sync --project "$SKILL_DIR" --no-dev
+else
+  log "uv environment already ready: $SKILL_DIR/.venv"
+fi

package/skills/sophnet-docx/src/scripts/office/helpers/merge_runs.py

@@ -1,199 +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)
+"""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)