fix: padacioso speed

.github/workflows/unit_tests.yml

@@ -13,12 +13,12 @@ jobs:
     strategy:
       max-parallel: 2
       matrix:
-        python-version: [ 3.7, 3.8, 3.9, '3.10' ]
+        python-version: [3.9, "3.10", "3.11", "3.12", "3.13"]
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - name: Set up python ${{ matrix.python-version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install System Dependencies

.gitignore

@@ -0,0 +1,216 @@
+# 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
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# 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
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

padacioso/__init__.py

@@ -1,4 +1,3 @@
-import concurrent.futures
 from typing import List, Iterator, Optional
 
 import simplematch
@@ -15,7 +14,6 @@
 
     from difflib import SequenceMatcher
 
-
     def fuzzy_match(x, against):
         """Perform a 'fuzzy' comparison between two strings.
         Returns:
@@ -38,6 +36,10 @@ def __init__(self, fuzz=False, n_workers=4):
         self.excluded_keywords = {}
         self.excluded_contexts = {}
 
+        # Cache for optimization - pre-built list for fast iteration
+        self._intent_list = []  # Pre-built list of (intent_name, regexes)
+        self._cache_dirty = True  # Flag to rebuild cache on next query
+
         if "word" not in simplematch.types:
             LOG.debug(f"Registering `word` type")
             _init_sm_word_type()
@@ -93,6 +95,7 @@ def remove_intent(self, name: str):
                     self._cased_matchers.pop(rx)
                 if rx in self._uncased_matchers:
                     self._uncased_matchers.pop(rx)
+            self._cache_dirty = True  # Mark cache as needing rebuild
 
     def add_entity(self, name: str, lines: List[str]):
         """
@@ -118,6 +121,15 @@ def remove_entity(self, name: str):
         if name in self.entity_samples:
             del self.entity_samples[name]
 
+    def _rebuild_cache(self):
+        """
+        Rebuild cached intent metadata for fast filtering.
+        Called lazily on first query after registration to avoid O(n²) during bulk registration.
+        """
+        # Pre-build the intent list to avoid reconstructing it every query
+        self._intent_list = list(self.intent_samples.items())
+        self._cache_dirty = False
+
     def _filter(self, query: str):
         # filter intents based on context/excluded keywords
         excluded_intents = []
@@ -205,28 +217,33 @@ def _fuzzy_score(self, query, s, penalty=0.25):
         score = (fuzzy_score + base_score) / 2
 
         if entities is not None:
-            return {"entities": entities or {},
-                    "conf": (fuzzy_score + base_score) / 2}
+            return {"entities": entities or {}, "conf": score}
 
     def calc_intents(self, query: str) -> Iterator[dict]:
         """
         Determine possible intents for a given query
         @param query: input to evaluate for an intent match
         @return: yields dict intent matches
         """
-        # filter intents based on context/excluded keywords
+        # Lazy cache rebuild - only rebuild once after bulk registration
+        # This avoids O(n²) scaling during registration (rebuild on every add)
+        if self._cache_dirty:
+            self._rebuild_cache()
+
+        # Filter based on runtime context/keywords (query and session dependent)
         excluded_intents = self._filter(query)
 
-        # do the work in parallel instead of sequentially
-        with concurrent.futures.ProcessPoolExecutor(max_workers=self.workers) as executor:
-            future_to_source = {
-                executor.submit(self._match, query, intent_name, regexes): intent_name
-                for intent_name, regexes in self.intent_samples.items() if intent_name not in excluded_intents
-            }
-            for future in concurrent.futures.as_completed(future_to_source):
-                res = future.result()
-                if res is not None:
-                    yield res
+        # Sequential processing - threading overhead > actual work for regex matching
+        for intent_name, regexes in self._intent_list:
+            if intent_name in excluded_intents:
+                continue
+            res = self._match(query, intent_name, regexes)
+            if res is not None:
+                yield res
+                # Early exit optimization: perfect match found
+                # TODO: Some validation that we don't have duplicates, and warning if we do
+                if res.get("conf", 0) == 1.0:
+                    return
 
     def calc_intent(self, query: str) -> Optional[dict]:
         """
@@ -260,6 +277,7 @@ def exclude_keywords(self, intent_name, samples):
             self.excluded_keywords[intent_name] = samples
         else:
             self.excluded_keywords[intent_name] += samples
+        self._cache_dirty = True  # Mark cache as needing rebuild
 
     def set_context(self, intent_name, context_name, context_val=None):
         if intent_name not in self.available_contexts:
@@ -271,11 +289,12 @@ def exclude_context(self, intent_name, context_name):
             self.excluded_contexts[intent_name] = [context_name]
         else:
             self.excluded_contexts[intent_name].append(context_name)
+        self._cache_dirty = True  # Mark cache as needing rebuild
 
     def unexclude_context(self, intent_name, context_name):
         if intent_name in self.excluded_contexts:
-            self.excluded_contexts[intent_name] = [c for c in self.excluded_contexts[intent_name]
-                                                   if context_name != c]
+            self.excluded_contexts[intent_name] = [c for c in self.excluded_contexts[intent_name] if context_name != c]
+        self._cache_dirty = True  # Mark cache as needing rebuild
 
     def unset_context(self, intent_name, context_name):
         if intent_name in self.available_contexts:
@@ -287,11 +306,12 @@ def require_context(self, intent_name, context_name):
             self.required_contexts[intent_name] = [context_name]
         else:
             self.required_contexts[intent_name].append(context_name)
+        self._cache_dirty = True  # Mark cache as needing rebuild
 
     def unrequire_context(self, intent_name, context_name):
         if intent_name in self.required_contexts:
-            self.required_contexts[intent_name] = [c for c in self.required_contexts[intent_name]
-                                                   if context_name != c]
+            self.required_contexts[intent_name] = [c for c in self.required_contexts[intent_name] if context_name != c]
+            self._cache_dirty = True  # Mark cache as needing rebuild
 
 
 def _init_sm_word_type():