Initial commit: 25 scripts Python sauvegardés
Date: 2026-08-28 11:43:34 EDT
This commit is contained in:
@@ -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)
|
||||
@@ -0,0 +1,167 @@
|
||||
---
|
||||
name: jupyter-live-kernel
|
||||
description: "Iterative Python via live Jupyter kernel (hamelnb)."
|
||||
version: 1.0.0
|
||||
author: Hermes Agent
|
||||
license: MIT
|
||||
platforms: [linux, macos, windows]
|
||||
metadata:
|
||||
hermes:
|
||||
tags: [jupyter, notebook, repl, data-science, exploration, iterative]
|
||||
category: data-science
|
||||
---
|
||||
|
||||
# Jupyter Live Kernel (hamelnb)
|
||||
|
||||
Gives you a **stateful Python REPL** via a live Jupyter kernel. Variables persist
|
||||
across executions. Use this instead of `execute_code` when you need to build up
|
||||
state incrementally, explore APIs, inspect DataFrames, or iterate on complex code.
|
||||
|
||||
## When to Use This vs Other Tools
|
||||
|
||||
| Tool | Use When |
|
||||
|------|----------|
|
||||
| **This skill** | Iterative exploration, state across steps, data science, ML, "let me try this and check" |
|
||||
| `execute_code` | One-shot scripts needing hermes tool access (web_search, file ops). Stateless. |
|
||||
| `terminal` | Shell commands, builds, installs, git, process management |
|
||||
|
||||
**Rule of thumb:** If you'd want a Jupyter notebook for the task, use this skill.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
1. **uv** must be installed (check: `which uv`)
|
||||
2. **JupyterLab** must be installed: `uv tool install jupyterlab`
|
||||
3. A Jupyter server must be running (see Setup below)
|
||||
|
||||
## Setup
|
||||
|
||||
The hamelnb script location:
|
||||
```
|
||||
SCRIPT="$HOME/.agent-skills/hamelnb/skills/jupyter-live-kernel/scripts/jupyter_live_kernel.py"
|
||||
```
|
||||
|
||||
If not cloned yet:
|
||||
```
|
||||
git clone https://github.com/hamelsmu/hamelnb.git ~/.agent-skills/hamelnb
|
||||
```
|
||||
|
||||
### Starting JupyterLab
|
||||
|
||||
Check if a server is already running:
|
||||
```
|
||||
uv run "$SCRIPT" servers
|
||||
```
|
||||
|
||||
If no servers found, start one:
|
||||
```
|
||||
jupyter-lab --no-browser --port=8888 --notebook-dir=$HOME/notebooks \
|
||||
--IdentityProvider.token='' --ServerApp.password='' > /tmp/jupyter.log 2>&1 &
|
||||
sleep 3
|
||||
```
|
||||
|
||||
Note: Token/password disabled for local agent access. The server runs headless.
|
||||
|
||||
### Creating a Notebook for REPL Use
|
||||
|
||||
If you just need a REPL (no existing notebook), create a minimal notebook file:
|
||||
```
|
||||
mkdir -p ~/notebooks
|
||||
```
|
||||
Write a minimal .ipynb JSON file with one empty code cell, then start a kernel
|
||||
session via the Jupyter REST API:
|
||||
```
|
||||
curl -s -X POST http://127.0.0.1:8888/api/sessions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"path":"scratch.ipynb","type":"notebook","name":"scratch.ipynb","kernel":{"name":"python3"}}'
|
||||
```
|
||||
|
||||
## Core Workflow
|
||||
|
||||
All commands return structured JSON. Always use `--compact` to save tokens.
|
||||
|
||||
### 1. Discover servers and notebooks
|
||||
|
||||
```
|
||||
uv run "$SCRIPT" servers --compact
|
||||
uv run "$SCRIPT" notebooks --compact
|
||||
```
|
||||
|
||||
### 2. Execute code (primary operation)
|
||||
|
||||
```
|
||||
uv run "$SCRIPT" execute --path <notebook.ipynb> --code '<python code>' --compact
|
||||
```
|
||||
|
||||
State persists across execute calls. Variables, imports, objects all survive.
|
||||
|
||||
Multi-line code works with $'...' quoting:
|
||||
```
|
||||
uv run "$SCRIPT" execute --path scratch.ipynb --code $'import os\nfiles = os.listdir(".")\nprint(f"Found {len(files)} files")' --compact
|
||||
```
|
||||
|
||||
### 3. Inspect live variables
|
||||
|
||||
```
|
||||
uv run "$SCRIPT" variables --path <notebook.ipynb> list --compact
|
||||
uv run "$SCRIPT" variables --path <notebook.ipynb> preview --name <varname> --compact
|
||||
```
|
||||
|
||||
### 4. Edit notebook cells
|
||||
|
||||
```
|
||||
# View current cells
|
||||
uv run "$SCRIPT" contents --path <notebook.ipynb> --compact
|
||||
|
||||
# Insert a new cell
|
||||
uv run "$SCRIPT" edit --path <notebook.ipynb> insert \
|
||||
--at-index <N> --cell-type code --source '<code>' --compact
|
||||
|
||||
# Replace cell source (use cell-id from contents output)
|
||||
uv run "$SCRIPT" edit --path <notebook.ipynb> replace-source \
|
||||
--cell-id <id> --source '<new code>' --compact
|
||||
|
||||
# Delete a cell
|
||||
uv run "$SCRIPT" edit --path <notebook.ipynb> delete --cell-id <id> --compact
|
||||
```
|
||||
|
||||
### 5. Verification (restart + run all)
|
||||
|
||||
Only use when the user asks for a clean verification or you need to confirm
|
||||
the notebook runs top-to-bottom:
|
||||
|
||||
```
|
||||
uv run "$SCRIPT" restart-run-all --path <notebook.ipynb> --save-outputs --compact
|
||||
```
|
||||
|
||||
## Practical Tips from Experience
|
||||
|
||||
1. **First execution after server start may timeout** — the kernel needs a moment
|
||||
to initialize. If you get a timeout, just retry.
|
||||
|
||||
2. **The kernel Python is JupyterLab's Python** — packages must be installed in
|
||||
that environment. If you need additional packages, install them into the
|
||||
JupyterLab tool environment first.
|
||||
|
||||
3. **--compact flag saves significant tokens** — always use it. JSON output can
|
||||
be very verbose without it.
|
||||
|
||||
4. **For pure REPL use**, create a scratch.ipynb and don't bother with cell editing.
|
||||
Just use `execute` repeatedly.
|
||||
|
||||
5. **Argument order matters** — subcommand flags like `--path` go BEFORE the
|
||||
sub-subcommand. E.g.: `variables --path nb.ipynb list` not `variables list --path nb.ipynb`.
|
||||
|
||||
6. **If a session doesn't exist yet**, you need to start one via the REST API
|
||||
(see Setup section). The tool can't execute without a live kernel session.
|
||||
|
||||
7. **Errors are returned as JSON** with traceback — read the `ename` and `evalue`
|
||||
fields to understand what went wrong.
|
||||
|
||||
8. **Occasional websocket timeouts** — some operations may timeout on first try,
|
||||
especially after a kernel restart. Retry once before escalating.
|
||||
|
||||
## Timeout Defaults
|
||||
|
||||
The script has a 30-second default timeout per execution. For long-running
|
||||
operations, pass `--timeout 120`. Use generous timeouts (60+) for initial
|
||||
setup or heavy computation.
|
||||
@@ -0,0 +1,3 @@
|
||||
---
|
||||
description: Diagram creation skills for generating visual diagrams, flowcharts, architecture diagrams, and illustrations using tools like Excalidraw.
|
||||
---
|
||||
Reference in New Issue
Block a user