deploy at 2025-12-28 11:51:35.372233

.gitignore

@@ -0,0 +1,207 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/

Dependency length.ipynb

@@ -0,0 +1,801 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2e1aaddb-8d3e-4168-b6b1-787b052c8244",
+   "metadata": {},
+   "source": [
+    "The plan is to first write a function for converting UD to SSUD, then measure dependency lengths."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e50c5f7a-75c3-40b3-89be-82988d8bfb73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import spacy\n",
+    "from spacy import displacy\n",
+    "\n",
+    "nlp = spacy.load(\"en_core_web_sm\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c49f475d-547f-49d8-8550-2f1ad1555a14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "relations = {\n",
+    "    \"subj\": [\"nsubj\", \"nsubjpass\", \"csubj\", \"csubjpass\", \"expl\"],\n",
+    "    \"comp\": [\"dobj\", \"dative\", \"attr\", \"oprd\", \"pobj\", \"aux\", \"auxpass\", \"mark\", \"case\", \"ccomp\", \"xcomp\", \"acomp\"],\n",
+    "    \"mod\": [\"agent\", \"advmod\", \"advcl\", \"relcl\", \"npmod\", \"npadvmod\", \"prt\"],\n",
+    "    \"udep\": [\"acl\", \"amod\", \"nmod\", \"poss\", \"nummod\", \"prep\"],\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "cefdbf22-b747-4bea-b279-c9b01e75ff2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def ssudify(doc):\n",
+    "    for token in doc:\n",
+    "        to_reverse = [token]\n",
+    "        for child in token.children:\n",
+    "            if (child.dep_ in [\"aux\", \"auxpass\", \"mark\", \"case\"]) or (child.dep_ == \"advmod\" and child.pos_ == \"SCONJ\"):\n",
+    "                to_reverse.append(child)\n",
+    "        to_reverse.sort(key = lambda x: abs(x.i - token.i))\n",
+    "        if len(to_reverse) > 1:\n",
+    "            for i in range(1, len(to_reverse)):\n",
+    "                if to_reverse[i].dep_ in [\"aux\", \"auxpass\"]:\n",
+    "                    for child in to_reverse[i-1].children:\n",
+    "                        if child.dep_ in relations[\"subj\"] + relations[\"mod\"] + [\"conj\", \"cc\"]:\n",
+    "                            child.head = to_reverse[i]\n",
+    "                to_reverse[i].head = to_reverse[i-1].head if to_reverse[i-1].head != to_reverse[i-1] else to_reverse[i]\n",
+    "                to_reverse[i].dep_ = to_reverse[i-1].dep_\n",
+    "                to_reverse[i-1].head = to_reverse[i]\n",
+    "                to_reverse[i-1].dep_ = \"comp\"\n",
+    "    for token in doc:\n",
+    "        if token.dep_ == \"dep\": token.dep_ = \"unknown\"\n",
+    "        for rel in relations.keys():\n",
+    "            if token.dep_ in relations[rel]: token.dep_ = rel\n",
+    "    for token in doc:\n",
+    "        subjects = sorted([child for child in token.children if child.dep_ == \"subj\"], key = lambda x: abs(x.i - token.i))\n",
+    "        if len(subjects) > 1:\n",
+    "            for s in subjects[1:]:\n",
+    "                s.dep_ = \"comp\"\n",
+    "    for token in doc:\n",
+    "        subject = [child for child in token.children if child.dep_ == \"subj\"]\n",
+    "        if subject:\n",
+    "            for child in [c for c in token.children if c.i < subject[0].i]:\n",
+    "                if child.dep_ in [\"comp\", \"udep\"]:\n",
+    "                    child.dep_ = \"mod\"\n",
+    "    return doc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "id": "23efda66-9d58-4169-9fa0-05de47267b5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def flyover(token):\n",
+    "    if token.dep_ in [\"subj\", \"comp\", \"udep\", \"conj\"]:\n",
+    "        dep_distance = abs(token.i - token.head.i)\n",
+    "        if token.head.i < token.i:\n",
+    "            return (token.doc[token.head.i+1:token.i], dep_distance - 1)\n",
+    "        elif token.head.i > token.i:\n",
+    "            return (token.doc[token.i+1:token.head.i], dep_distance - 1)\n",
+    "    else:\n",
+    "        return (token.doc[token.i:token.i], 0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "5bb29f0a-9d55-4f2d-84c3-4c3c4bae0271",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_fluff(doc):\n",
+    "    flyovers = list(map(flyover, doc))\n",
+    "    flyovers = [f for f in flyovers if len(f[0]) > 0]\n",
+    "    flyovers = [f1 for f1 in flyovers if len([f2 for f2 in flyovers if \n",
+    "                                              (f2[0][-1].i > f1[0][0].i >= f2[0][0].i or f2[0][0].i < f1[0][-1].i <= f2[0][-1].i) and \n",
+    "                                              (len(f1[0]) < len(f2[0]) or f1[1] < f2[1])]) == 0 and len(f1[0]) > 2]\n",
+    "    flyovers = sorted(flyovers, key=lambda x: x[0][0].i)\n",
+    "    interstices = []\n",
+    "    for i in range(len(flyovers)):\n",
+    "        if i == 0:\n",
+    "            if flyovers[0][0][0].i > 0:\n",
+    "                interstices.append((doc[0:flyovers[0][0][0].i], 0))\n",
+    "        else:\n",
+    "            if flyovers[i][0][0].i > flyovers[i-1][0][-1].i + 1:\n",
+    "                interstices.append((doc[flyovers[i-1][0][-1].i+1:flyovers[i][0][0].i], 0))\n",
+    "            # elif flyovers[i][1] == flyovers[i-1][1]:\n",
+    "            #     flyovers[i] = (doc[flyovers[i-1][0][0].i:flyovers[i][0][-1].i+1], flyovers[i][1])\n",
+    "            #     flyovers[i-1] = (doc[flyovers[i-1][0][0].i:flyovers[i-1][0][0].i], flyovers[i-1][1])\n",
+    "    if len(flyovers) > 0:\n",
+    "        if flyovers[-1][0][-1].i < doc[-1].i:\n",
+    "            interstices.append((doc[flyovers[-1][0][-1].i+1:], 0))\n",
+    "    else:\n",
+    "        interstices.append((doc, 0))\n",
+    "    flyovers = [f for f in flyovers if len(f[0]) > 0]\n",
+    "    return sorted(flyovers + interstices, key=lambda x: x[0][0].i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "id": "ba90ff19-c665-49d8-8ad4-5caee885901d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<span class=\"tex2jax_ignore\"><svg xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\" xml:lang=\"en\" id=\"0c70d09209f64114aa5a12db7f67e2b2-0\" class=\"displacy\" width=\"6350\" height=\"574.5\" direction=\"ltr\" style=\"max-width: none; height: 574.5px; color: #000000; background: #ffffff; font-family: Arial; direction: ltr\">\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"50\">According</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"50\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"225\">to</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"225\">ADP</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"400\">the</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"400\">DET</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"575\">studies, “</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"575\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"750\">People</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"750\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"925\">who</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"925\">PRON</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1100\">danced</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1100\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1275\">more</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1275\">ADJ</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1450\">than</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1450\">ADP</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1625\">once</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1625\">ADV</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1800\">a</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1800\">DET</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"1975\">week</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"1975\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"2150\">had</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"2150\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"2325\">a</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"2325\">DET</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"2500\">76%</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"2500\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"2675\">lower</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"2675\">ADJ</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"2850\">risk</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"2850\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3025\">of</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3025\">ADP</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3200\">getting</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3200\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3375\">dementia</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3375\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3550\">compared</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3550\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3725\">to</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3725\">ADP</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"3900\">people</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"3900\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4075\">who</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4075\">PRON</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4250\">danced</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4250\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4425\">less</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4425\">ADV</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4600\">frequently</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4600\">ADV</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4775\">or</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4775\">CCONJ</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"4950\">did</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"4950\">AUX</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"5125\">n’t</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"5125\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"5300\">dance</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"5300\">NOUN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"5475\">at</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"5475\">ADV</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"5650\">all,”</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"5650\">ADV</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"5825\">Dr</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"5825\">PROPN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"6000\">Pasricha</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"6000\">PROPN</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<text class=\"displacy-token\" fill=\"currentColor\" text-anchor=\"middle\" y=\"484.5\">\n",
+       "    <tspan class=\"displacy-word\" fill=\"currentColor\" x=\"6175\">noted.</tspan>\n",
+       "    <tspan class=\"displacy-tag\" dy=\"2em\" fill=\"currentColor\" x=\"6175\">VERB</tspan>\n",
+       "</text>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-0\" stroke-width=\"2px\" d=\"M70,439.5 C70,89.5 2145.0,89.5 2145.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-0\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M70,441.5 L62,429.5 78,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-1\" stroke-width=\"2px\" d=\"M70,439.5 C70,352.0 205.0,352.0 205.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-1\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M205.0,441.5 L213.0,429.5 197.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-2\" stroke-width=\"2px\" d=\"M420,439.5 C420,352.0 555.0,352.0 555.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-2\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M420,441.5 L412,429.5 428,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-3\" stroke-width=\"2px\" d=\"M245,439.5 C245,264.5 560.0,264.5 560.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-3\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M560.0,441.5 L568.0,429.5 552.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-4\" stroke-width=\"2px\" d=\"M770,439.5 C770,177.0 2140.0,177.0 2140.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-4\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M770,441.5 L762,429.5 778,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-5\" stroke-width=\"2px\" d=\"M945,439.5 C945,352.0 1080.0,352.0 1080.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-5\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M945,441.5 L937,429.5 953,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-6\" stroke-width=\"2px\" d=\"M770,439.5 C770,264.5 1085.0,264.5 1085.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-6\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1085.0,441.5 L1093.0,429.5 1077.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-7\" stroke-width=\"2px\" d=\"M1120,439.5 C1120,352.0 1255.0,352.0 1255.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-7\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1255.0,441.5 L1263.0,429.5 1247.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-8\" stroke-width=\"2px\" d=\"M1295,439.5 C1295,352.0 1430.0,352.0 1430.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-8\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1430.0,441.5 L1438.0,429.5 1422.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-9\" stroke-width=\"2px\" d=\"M1470,439.5 C1470,352.0 1605.0,352.0 1605.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-9\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pcomp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1605.0,441.5 L1613.0,429.5 1597.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-10\" stroke-width=\"2px\" d=\"M1820,439.5 C1820,352.0 1955.0,352.0 1955.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-10\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1820,441.5 L1812,429.5 1828,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-11\" stroke-width=\"2px\" d=\"M1295,439.5 C1295,264.5 1960.0,264.5 1960.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-11\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M1960.0,441.5 L1968.0,429.5 1952.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-12\" stroke-width=\"2px\" d=\"M2170,439.5 C2170,2.0 6175.0,2.0 6175.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-12\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M2170,441.5 L2162,429.5 2178,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-13\" stroke-width=\"2px\" d=\"M2345,439.5 C2345,264.5 2835.0,264.5 2835.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-13\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">det</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M2345,441.5 L2337,429.5 2353,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-14\" stroke-width=\"2px\" d=\"M2520,439.5 C2520,352.0 2655.0,352.0 2655.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-14\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M2520,441.5 L2512,429.5 2528,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-15\" stroke-width=\"2px\" d=\"M2695,439.5 C2695,352.0 2830.0,352.0 2830.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-15\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M2695,441.5 L2687,429.5 2703,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-16\" stroke-width=\"2px\" d=\"M2170,439.5 C2170,177.0 2840.0,177.0 2840.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-16\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M2840.0,441.5 L2848.0,429.5 2832.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-17\" stroke-width=\"2px\" d=\"M2870,439.5 C2870,352.0 3005.0,352.0 3005.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-17\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3005.0,441.5 L3013.0,429.5 2997.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-18\" stroke-width=\"2px\" d=\"M3045,439.5 C3045,352.0 3180.0,352.0 3180.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-18\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">pcomp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3180.0,441.5 L3188.0,429.5 3172.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-19\" stroke-width=\"2px\" d=\"M3220,439.5 C3220,352.0 3355.0,352.0 3355.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-19\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3355.0,441.5 L3363.0,429.5 3347.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-20\" stroke-width=\"2px\" d=\"M2170,439.5 C2170,89.5 3545.0,89.5 3545.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-20\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3545.0,441.5 L3553.0,429.5 3537.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-21\" stroke-width=\"2px\" d=\"M3570,439.5 C3570,352.0 3705.0,352.0 3705.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-21\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">udep</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3705.0,441.5 L3713.0,429.5 3697.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-22\" stroke-width=\"2px\" d=\"M3745,439.5 C3745,352.0 3880.0,352.0 3880.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-22\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M3880.0,441.5 L3888.0,429.5 3872.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-23\" stroke-width=\"2px\" d=\"M4095,439.5 C4095,352.0 4230.0,352.0 4230.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-23\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4095,441.5 L4087,429.5 4103,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-24\" stroke-width=\"2px\" d=\"M3920,439.5 C3920,264.5 4235.0,264.5 4235.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-24\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4235.0,441.5 L4243.0,429.5 4227.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-25\" stroke-width=\"2px\" d=\"M4445,439.5 C4445,352.0 4580.0,352.0 4580.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-25\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4445,441.5 L4437,429.5 4453,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-26\" stroke-width=\"2px\" d=\"M4270,439.5 C4270,264.5 4585.0,264.5 4585.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-26\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4585.0,441.5 L4593.0,429.5 4577.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-27\" stroke-width=\"2px\" d=\"M4270,439.5 C4270,177.0 4765.0,177.0 4765.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-27\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">cc</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4765.0,441.5 L4773.0,429.5 4757.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-28\" stroke-width=\"2px\" d=\"M4270,439.5 C4270,89.5 4945.0,89.5 4945.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-28\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">conj</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M4945.0,441.5 L4953.0,429.5 4937.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-29\" stroke-width=\"2px\" d=\"M4970,439.5 C4970,352.0 5105.0,352.0 5105.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-29\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">punct</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M5105.0,441.5 L5113.0,429.5 5097.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-30\" stroke-width=\"2px\" d=\"M4970,439.5 C4970,264.5 5285.0,264.5 5285.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-30\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">comp</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M5285.0,441.5 L5293.0,429.5 5277.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-31\" stroke-width=\"2px\" d=\"M5495,439.5 C5495,352.0 5630.0,352.0 5630.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-31\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M5495,441.5 L5487,429.5 5503,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-32\" stroke-width=\"2px\" d=\"M4970,439.5 C4970,177.0 5640.0,177.0 5640.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-32\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">mod</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M5640.0,441.5 L5648.0,429.5 5632.0,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-33\" stroke-width=\"2px\" d=\"M5845,439.5 C5845,352.0 5980.0,352.0 5980.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-33\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">compound</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M5845,441.5 L5837,429.5 5853,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "\n",
+       "<g class=\"displacy-arrow\">\n",
+       "    <path class=\"displacy-arc\" id=\"arrow-0c70d09209f64114aa5a12db7f67e2b2-0-34\" stroke-width=\"2px\" d=\"M6020,439.5 C6020,352.0 6155.0,352.0 6155.0,439.5\" fill=\"none\" stroke=\"currentColor\"/>\n",
+       "    <text dy=\"1.25em\" style=\"font-size: 0.8em; letter-spacing: 1px\">\n",
+       "        <textPath xlink:href=\"#arrow-0c70d09209f64114aa5a12db7f67e2b2-0-34\" class=\"displacy-label\" startOffset=\"50%\" side=\"left\" fill=\"currentColor\" text-anchor=\"middle\">subj</textPath>\n",
+       "    </text>\n",
+       "    <path class=\"displacy-arrowhead\" d=\"M6020,441.5 L6012,429.5 6028,429.5\" fill=\"currentColor\"/>\n",
+       "</g>\n",
+       "</svg></span>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "doc = ssudify(nlp(\"According to the studies, “People who danced more than once a week had a 76% lower risk of getting dementia compared to people who danced less frequently or didn’t dance at all,” Dr Pasricha noted.\"))\n",
+    "# Since this is an interactive Jupyter environment, we can use displacy.render here\n",
+    "displacy.render(doc, style='dep')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "daa1e8f5-2afe-4153-9469-a4c2af9b46b1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[(Judgement, 0)]"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "get_fluff(doc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "b8dcf65d-89b0-49fd-9a0d-fc1454d522e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from fasthtml.common import *\n",
+    "from fasthtml.jupyter import JupyUvi, HTMX"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "9f23a19c-b645-4b78-85fd-bc9742d00f82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def display_annotations(annot):\n",
+    "    return Div(*[Span(a[0], style=f\"margin-right: 0.5ex; background: rgba(219, 144, 232, {a[1]/15})\") for a in annot])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "8fb35fe3-68de-45b6-8053-8b390c8e8661",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "app, rt = fast_app(pico=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "9ce9c318-733d-4ee1-b5d7-39d98aa14697",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@app.get\n",
+    "def index():\n",
+    "    page = Div(\n",
+    "        Form(hx_post=send, hx_target=\"#output\", hx_swap=\"outerHTML\")(\n",
+    "            Div(Button(\"Check\", style=\"margin-bottom: 1rem\"), \n",
+    "                Textarea(name=\"text\", style=\"height: calc(100vh - 11rem)\"))\n",
+    "            ),\n",
+    "        Div(\n",
+    "            Div(Small(Em(\"Highlighted text segments can be shortened or reordered to improve readability. The stronger the highlight, the more the segment burdens the reader’s memory.\")), \n",
+    "                cls=\"overflow-auto\", style=\"height: 4rem; text-wrap: balance; padding: 0rem 1rem\"),\n",
+    "            Div(id=\"output\", style=\"padding: 1rem; padding-bottom: calc(1rem - 5px)\")\n",
+    "        ),\n",
+    "        cls=\"grid\"\n",
+    "    )\n",
+    "    return Titled('Readability feedback', page)\n",
+    "\n",
+    "@app.post\n",
+    "def send(text:str):\n",
+    "    paragraphs = re.sub(r\"[^\\S\\r\\n]+\", \" \", text).split(\"\\r\\n\\r\\n\")\n",
+    "    docs = [ssudify(nlp(para)) for para in paragraphs]\n",
+    "    annot_paras = [get_fluff(doc) for doc in docs]\n",
+    "    return Div(*[P(*[Span(Span(a[0], style=f\"background: light-dark(rgba(237, 201, 241, {a[1]/15}), rgba(182, 69, 205, {a[1]/15}))\"), \n",
+    "                          Span(\" \")) for a in annot_para],\n",
+    "                   style=\"margin-bottom: 1.5em\")\n",
+    "                 for annot_para in annot_paras[:-1]],\n",
+    "               P(*[Span(Span(a[0], style=f\"background: light-dark(rgba(237, 201, 241, {a[1]/15}), rgba(182, 69, 205, {a[1]/15}))\"), \n",
+    "                        Span(\" \")) for a in annot_paras[-1]],\n",
+    "                 style=\"margin-bottom: 0em\"),\n",
+    "               id=\"output\", cls=\"overflow-auto\", style=\"height: calc(100vh - 11rem); padding: 1rem; padding-bottom: calc(1rem - 5px)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "4cc68772-d26d-4cd1-be59-c23a5739c3d0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "<script>\n",
+       "document.body.addEventListener('htmx:configRequest', (event) => {\n",
+       "    if(event.detail.path.includes('://')) return;\n",
+       "    htmx.config.selfRequestsOnly=false;\n",
+       "    event.detail.path = `${location.protocol}//${location.hostname}:8000${event.detail.path}`;\n",
+       "});\n",
+       "</script>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "server = JupyUvi(app)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "3e8c0a41-0d79-4715-ab2b-e5a2d0455569",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<iframe src=\"http://localhost:8000/\" style=\"width: 100%; height: auto; border: none;\" onload=\"{\n",
+       "        let frame = this;\n",
+       "        window.addEventListener('message', function(e) {\n",
+       "            if (e.source !== frame.contentWindow) return; // Only proceed if the message is from this iframe\n",
+       "            if (e.data.height) frame.style.height = (e.data.height+1) + 'px';\n",
+       "        }, false);\n",
+       "    }\" allow=\"accelerometer; autoplay; camera; clipboard-read; clipboard-write; display-capture; encrypted-media; fullscreen; gamepad; geolocation; gyroscope; hid; identity-credentials-get; idle-detection; magnetometer; microphone; midi; payment; picture-in-picture; publickey-credentials-get; screen-wake-lock; serial; usb; web-share; xr-spatial-tracking\"></iframe> "
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "HTMX()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "257f3c71-a034-4c9d-b35f-a9e06ddcd021",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "server.stop()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+WORKDIR /code
+COPY --link --chown=1000 . .
+RUN mkdir -p /tmp/cache/
+RUN chmod a+rwx -R /tmp/cache/
+ENV HF_HUB_CACHE=HF_HOME
+RUN pip install --no-cache-dir -r requirements.txt
+
+ENV PYTHONUNBUFFERED=1 PORT=7860
+CMD ["python", "main.py"]

README.md

@@ -1,10 +1,11 @@
 ---
-title: Readability Feedback
-emoji: 🐠
-colorFrom: green
-colorTo: red
+title: Readability feedback
+emoji: 📖
+colorFrom: red
+colorTo: purple
 sdk: docker
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# readability-feedback
+NLP-based readability feedback for writers

main.py

@@ -0,0 +1,125 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+import spacy
+
+nlp = spacy.load("en_core_web_sm")
+
+relations = {
+    "subj": ["nsubj", "nsubjpass", "csubj", "csubjpass", "expl"],
+    "comp": ["dobj", "dative", "attr", "oprd", "pobj", "aux", "auxpass", "mark", "case", "ccomp", "xcomp", "acomp"],
+    "mod": ["agent", "advmod", "advcl", "relcl", "npmod", "npadvmod", "prt"],
+    "udep": ["acl", "amod", "nmod", "poss", "nummod", "prep"],
+}
+
+def ssudify(doc):
+    for token in doc:
+        to_reverse = [token]
+        for child in token.children:
+            if (child.dep_ in ["aux", "auxpass", "mark", "case"]) or (child.dep_ == "advmod" and child.pos_ == "SCONJ"):
+                to_reverse.append(child)
+        to_reverse.sort(key = lambda x: abs(x.i - token.i))
+        if len(to_reverse) > 1:
+            for i in range(1, len(to_reverse)):
+                if to_reverse[i].dep_ in ["aux", "auxpass"]:
+                    for child in to_reverse[i-1].children:
+                        if child.dep_ in relations["subj"] + relations["mod"] + ["conj", "cc"]:
+                            child.head = to_reverse[i]
+                to_reverse[i].head = to_reverse[i-1].head if to_reverse[i-1].head != to_reverse[i-1] else to_reverse[i]
+                to_reverse[i].dep_ = to_reverse[i-1].dep_
+                to_reverse[i-1].head = to_reverse[i]
+                to_reverse[i-1].dep_ = "comp"
+    for token in doc:
+        if token.dep_ == "dep": token.dep_ = "unknown"
+        for rel in relations.keys():
+            if token.dep_ in relations[rel]: token.dep_ = rel
+    for token in doc:
+        subjects = sorted([child for child in token.children if child.dep_ == "subj"], key = lambda x: abs(x.i - token.i))
+        if len(subjects) > 1:
+            for s in subjects[1:]:
+                s.dep_ = "comp"
+    for token in doc:
+        subject = [child for child in token.children if child.dep_ == "subj"]
+        if subject:
+            for child in [c for c in token.children if c.i < subject[0].i]:
+                if child.dep_ in ["comp", "udep"]:
+                    child.dep_ = "mod"
+    return doc
+
+
+def flyover(token):
+    if token.dep_ in ["subj", "comp", "udep", "conj"]:
+        dep_distance = abs(token.i - token.head.i)
+        if token.head.i < token.i:
+            return (token.doc[token.head.i+1:token.i], dep_distance - 1)
+        elif token.head.i > token.i:
+            return (token.doc[token.i+1:token.head.i], dep_distance - 1)
+    else:
+        return (token.doc[token.i:token.i], 0)
+
+
+def get_fluff(doc):
+    flyovers = list(map(flyover, doc))
+    flyovers = [f for f in flyovers if len(f[0]) > 0]
+    flyovers = [f1 for f1 in flyovers if len([f2 for f2 in flyovers if 
+                                              (f2[0][-1].i > f1[0][0].i >= f2[0][0].i or f2[0][0].i < f1[0][-1].i <= f2[0][-1].i) and 
+                                              (len(f1[0]) < len(f2[0]) or f1[1] < f2[1])]) == 0 and len(f1[0]) > 2]
+    flyovers = sorted(flyovers, key=lambda x: x[0][0].i)
+    interstices = []
+    for i in range(len(flyovers)):
+        if i == 0:
+            if flyovers[0][0][0].i > 0:
+                interstices.append((doc[0:flyovers[0][0][0].i], 0))
+        else:
+            if flyovers[i][0][0].i > flyovers[i-1][0][-1].i + 1:
+                interstices.append((doc[flyovers[i-1][0][-1].i+1:flyovers[i][0][0].i], 0))
+            # elif flyovers[i][1] == flyovers[i-1][1]:
+            #     flyovers[i] = (doc[flyovers[i-1][0][0].i:flyovers[i][0][-1].i+1], flyovers[i][1])
+            #     flyovers[i-1] = (doc[flyovers[i-1][0][0].i:flyovers[i-1][0][0].i], flyovers[i-1][1])
+    if len(flyovers) > 0:
+        if flyovers[-1][0][-1].i < doc[-1].i:
+            interstices.append((doc[flyovers[-1][0][-1].i+1:], 0))
+    else:
+        interstices.append((doc, 0))
+    flyovers = [f for f in flyovers if len(f[0]) > 0]
+    return sorted(flyovers + interstices, key=lambda x: x[0][0].i)
+
+from fasthtml_hf import setup_hf_backup
+from fasthtml.common import *
+import re
+
+app, rt = fast_app(pico=True)
+
+
+@app.get
+def index():
+    page = Div(
+        Form(hx_post=send, hx_target="#output", hx_swap="outerHTML")(
+            Div(Button("Check", style="margin-bottom: 1rem"), 
+                Textarea(name="text", style="height: calc(100vh - 11rem)"))
+            ),
+        Div(
+            Div(Small(Em("Highlighted text segments can be shortened or reordered to improve readability. The stronger the highlight, the more the segment burdens the reader’s memory.")), 
+                cls="overflow-auto", style="height: 4rem; text-wrap: balance; padding: 0rem 1rem"),
+            Div(id="output", style="padding: 1rem; padding-bottom: calc(1rem - 5px)")
+        ),
+        cls="grid"
+    )
+    return Titled('Readability feedback', page)
+
+@app.post
+def send(text:str):
+    paragraphs = re.sub(r"[^\S\r\n]+", " ", text).split("\r\n\r\n")
+    docs = [ssudify(nlp(para)) for para in paragraphs]
+    annot_paras = [get_fluff(doc) for doc in docs]
+    return Div(*[P(*[Span(Span(a[0], style=f"background: light-dark(rgba(237, 201, 241, {a[1]/15}), rgba(182, 69, 205, {a[1]/15}))"), 
+                          Span(" ")) for a in annot_para],
+                   style="margin-bottom: 1.5em")
+                 for annot_para in annot_paras[:-1]],
+               P(*[Span(Span(a[0], style=f"background: light-dark(rgba(237, 201, 241, {a[1]/15}), rgba(182, 69, 205, {a[1]/15}))"), 
+                        Span(" ")) for a in annot_paras[-1]],
+                 style="margin-bottom: 0em"),
+               id="output", cls="overflow-auto", style="height: calc(100vh - 11rem); padding: 1rem; padding-bottom: calc(1rem - 5px)")
+
+setup_hf_backup(app)
+serve()

requirements.txt

@@ -0,0 +1,4 @@
+fasthtml-hf
+python-fasthtml
+spacy
+en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.8.0/en_core_web_sm-3.8.0-py3-none-any.whl