wxpath 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

wxpath/tui_settings.py

@@ -0,0 +1,151 @@
+"""Persistent TUI settings: load/save crawler-related options from a config file.
+
+pre-1.0.0 - APIs and contracts may change.
+
+Settings are stored in a single JSON file (e.g. ~/.config/wxpath/tui_settings.json).
+The schema is defined in TUISettingsSchema; adding a new setting requires one new
+entry in the schema and, if needed, use of that value where the crawler/engine
+is created.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+from typing import Any
+
+from wxpath.settings import CRAWLER_SETTINGS
+
+
+def _config_dir() -> Path:
+    """Return the wxpath config directory, creating it if needed."""
+    xdg_env = os.environ.get("XDG_CONFIG_HOME")
+    if xdg_env:
+        base = Path(xdg_env)
+    else:
+        base = Path.home() / ".config"
+    path = base / "wxpath"
+    path.mkdir(parents=True, exist_ok=True)
+    return path
+
+
+def get_tui_settings_path() -> Path:
+    """Return the path to the TUI settings JSON file."""
+    return _config_dir() / "tui_settings.json"
+
+
+# Schema: one dict per setting. 
+# Keys: key (file/API), label (display), type, default, optional min/max, help.
+# Defaults are taken from CRAWLER_SETTINGS so there is a single source of truth for built-in values.
+TUISettingsSchema: list[dict[str, Any]] = [
+    {
+        "key": "concurrency",
+        "label": "CONCURRENCY",
+        "type": "int",
+        "default": getattr(CRAWLER_SETTINGS, "concurrency", 16),
+        "min": 1,
+        "max": 256,
+        "help": "Maximum number of concurrent HTTP requests.",
+    },
+    {
+        "key": "per_host",
+        "label": "PER_HOST",
+        "type": "int",
+        "default": getattr(CRAWLER_SETTINGS, "per_host", 8),
+        "min": 1,
+        "max": 64,
+        "help": "Maximum concurrent requests per host.",
+    },
+    {
+        "key": "respect_robots",
+        "label": "RESPECT_ROBOTS",
+        "type": "bool",
+        "default": getattr(CRAWLER_SETTINGS, "respect_robots", True),
+        "help": "Whether to respect robots.txt directives.",
+    },
+    {
+        "key": "verify_ssl",
+        "label": "VERIFY_SSL",
+        "type": "bool",
+        "default": getattr(CRAWLER_SETTINGS, "verify_ssl", True),
+        "help": "Verify SSL certificates. Disable for sites with broken certificate chains.",
+    },
+]
+
+
+def _defaults_from_schema() -> dict[str, Any]:
+    """Build a dict of default values from the schema."""
+    return {s["key"]: s["default"] for s in TUISettingsSchema}
+
+
+def validate_tui_settings(settings: dict[str, Any]) -> list[str]:
+    """Validate all schema keys; return list of error messages (empty if valid)."""
+    errors = []
+    for key, value in settings.items():
+        try:
+            _validate_value(key, value, TUISettingsSchema)
+        except ValueError as e:
+            errors.append(str(e))
+    return errors
+
+
+def _validate_value(key: str, value: Any, schema: list[dict[str, Any]]) -> Any:
+    """Validate and coerce a single value. Returns the coerced value or raises ValueError."""
+    entry = next((e for e in schema if e["key"] == key), None)
+    if not entry:
+        raise ValueError(f"Unknown setting: {key}")
+    t = entry["type"]
+    if t == "int":
+        try:
+            v = int(value)
+        except (TypeError, ValueError):
+            raise ValueError(f"{key}: expected integer, got {type(value).__name__}") from None
+        min_v = entry.get("min")
+        max_v = entry.get("max")
+        if min_v is not None and v < min_v:
+            raise ValueError(f"{key}: must be >= {min_v}")
+        if max_v is not None and v > max_v:
+            raise ValueError(f"{key}: must be <= {max_v}")
+        return v
+    if t == "bool":
+        if isinstance(value, bool):
+            return value
+        if isinstance(value, str):
+            return value.strip().lower() in ("1", "true", "yes", "on")
+        return bool(value)
+    return value
+
+
+def load_tui_settings() -> dict[str, Any]:
+    """Load TUI settings from the config file. Missing or invalid keys use schema defaults."""
+    path = get_tui_settings_path()
+    defaults = _defaults_from_schema()
+    if not path.exists():
+        return defaults
+    try:
+        raw = json.loads(path.read_text(encoding="utf-8"))
+    except (OSError, json.JSONDecodeError):
+        return defaults
+    if not isinstance(raw, dict):
+        return defaults
+    result = dict(defaults)
+    for key in result:
+        if key not in raw:
+            continue
+        try:
+            result[key] = _validate_value(key, raw[key], TUISettingsSchema)
+        except ValueError:
+            pass
+    return result
+
+
+def save_tui_settings(settings: dict[str, Any]) -> None:
+    """Save TUI settings to the config file. Only schema keys are written."""
+    path = get_tui_settings_path()
+    schema_keys = {s["key"] for s in TUISettingsSchema}
+    to_write = {k: v for k, v in settings.items() if k in schema_keys}
+    for key in schema_keys:
+        if key not in to_write:
+            to_write[key] = _defaults_from_schema()[key]
+    path.write_text(json.dumps(to_write, indent=2), encoding="utf-8")

wxpath/util/cleaners.py

@@ -0,0 +1,31 @@
+from collections import Counter
+
+from wxpath.util.common_paths import XPATH_PATH_TO_TEXT_NODE_PARENTS
+
+
+def main_text_extractor(element):
+    """Inspired by my eatiht implementation:
+    https://github.com/rodricios/eatiht
+    """
+    try:
+        xpath_finder = element.getroot().getroottree().getpath
+    except(AttributeError):
+        xpath_finder = element.getroottree().getpath
+
+    nodes_with_text = element.xpath(XPATH_PATH_TO_TEXT_NODE_PARENTS)
+
+    sent_xpath_pairs = [
+        # hard-code paragraph breaks (there has to be a better way)
+        (n , xpath_finder(n))
+        for n in nodes_with_text
+    ]
+
+    parent_paths = [p.rsplit('/', 1)[0] for s, p in sent_xpath_pairs]
+
+    # build frequency distribution
+    max_path = Counter(parent_paths).most_common()[0][0]
+
+    article_text = ' '.join([''.join(s.xpath('.//text()')) 
+                             for (s, x) in sent_xpath_pairs if max_path in x])
+
+    return article_text

wxpath/util/common_paths.py

@@ -0,0 +1,22 @@
+XPATH_BOOL_INTERNAL_LINKS = (
+    "    not(starts-with(., 'http')) or "  # Relative links
+    "    contains(., '://{0}') or "        # Root domain match
+    "    contains(., '.{0}')"              # Subdomain match
+)
+XPATH_BOOL_EXTERNAL_LINKS = "not(" + XPATH_BOOL_INTERNAL_LINKS + ")"
+
+# allows for false positives
+XPATH_PATH_TO_INTERNAL_LINKS = "//a/@href[" + XPATH_BOOL_INTERNAL_LINKS + "]"
+XPATH_PATH_TO_EXTERNAL_LINKS = "//a/@href[" + XPATH_BOOL_EXTERNAL_LINKS + "]" 
+
+XPATH_PATH_TO_TEXT_NODE_PARENTS = '//body\
+                        //*[not(\
+                            self::script or \
+                            self::noscript or \
+                            self::style or \
+                            self::i or \
+                            self::b or \
+                            self::strong or \
+                            self::span or \
+                            self::a)] \
+                            /text()[string-length(normalize-space()) > 20]/..'

wxpath/util/logging.py

@@ -59,13 +59,9 @@ def configure_logging(level: str | int = "INFO", **overrides) -> None:
 
     Call this once in an application entry-point **or** rely on defaults.
 
-    Parameters
-    ----------
-    level
-        "DEBUG"|"INFO"|... or `logging.DEBUG`, overrides the root wxpath logger.
-    overrides
-        Dict that is merged (shallow) into the default dictConfig.
-        Lets advanced users swap formatters/handlers.
+    Args:
+        level (str | int): Logging level to configure. Defaults to "INFO".
+        **overrides: Additional logging configuration overrides
     """
     conf = {**_DEFAULT_LOGGING_CONF, **overrides}
     conf["loggers"]["wxpath"]["level"] = level

{wxpath-0.4.0.dist-info → wxpath-0.5.0.dist-info}/METADATA

@@ -1,9 +1,14 @@
 Metadata-Version: 2.4
 Name: wxpath
-Version: 0.4.0
+Version: 0.5.0
 Summary: wxpath - a declarative web crawler and data extractor
 Author-email: Rodrigo Palacios <rodrigopala91@gmail.com>
 License-Expression: MIT
+Project-URL: Homepage, https://rodricios.github.io/wxpath
+Project-URL: Documentation, https://rodricios.github.io/wxpath
+Project-URL: Repository, https://github.com/rodricios/wxpath
+Project-URL: Issues, https://github.com/rodricios/wxpath/issues
+Project-URL: Changelog, https://github.com/rodricios/wxpath/blob/main/CHANGELOG.md
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -17,27 +22,112 @@ Provides-Extra: cache-sqlite
 Requires-Dist: aiohttp-client-cache[sqlite]; extra == "cache-sqlite"
 Provides-Extra: cache-redis
 Requires-Dist: aiohttp-client-cache[redis]; extra == "cache-redis"
+Provides-Extra: llm
+Requires-Dist: langchain>=1.0.0; extra == "llm"
+Requires-Dist: langchain-core>=1.0.0; extra == "llm"
+Requires-Dist: langchain-ollama>=1.0.0; extra == "llm"
+Requires-Dist: langchain-community>=0.4.0; extra == "llm"
+Requires-Dist: langchain-chroma>=1.0.0; extra == "llm"
+Requires-Dist: chromadb>=1.0.0; extra == "llm"
+Requires-Dist: langchain-text-splitters>=1.1.0; extra == "llm"
 Provides-Extra: test
 Requires-Dist: pytest>=7.0; extra == "test"
 Requires-Dist: pytest-asyncio>=0.23; extra == "test"
 Provides-Extra: dev
 Requires-Dist: ruff; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: mkdocs>=1.5; extra == "docs"
+Requires-Dist: mkdocs-material>=9.0; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.24; extra == "docs"
+Requires-Dist: mkdocs-macros-plugin>=1.0; extra == "docs"
+Requires-Dist: mkdocs-resize-images>=1.0; extra == "docs"
+Requires-Dist: mkdocs-glightbox; extra == "docs"
+Requires-Dist: pyyaml>=6.0; extra == "docs"
+Provides-Extra: tui
+Requires-Dist: textual>=1.0.0; extra == "tui"
+Requires-Dist: aiohttp-client-cache>=0.14.0; extra == "tui"
+Requires-Dist: aiohttp-client-cache[sqlite]; extra == "tui"
 Dynamic: license-file
 
-# **wxpath** - declarative web crawling with XPath 
+# **wxpath** - declarative web graph traversal with XPath 
 
-[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/release/python-3100/)
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/release/python-3100/) [![Documentation Status](https://img.shields.io/badge/documentation-green.svg)](https://rodricios.github.io/wxpath)
+
+
+> NEW: [TUI](https://rodricios.github.io/wxpath/tui/quickstart.md) - Interactive terminal interface (powered by Textual) for testing wxpath expressions and exporting data.
+
+![Wxpath TUI Demo screenshot](docs/assets/images/demo1.jpg)
+
+## Install
+
+Requires Python 3.10+.
+
+```
+pip install wxpath
+# For TUI support
+pip install wxpath[tui]
+```
+---
+
+
+## What is wxpath?
 
 **wxpath** is a declarative web crawler where traversal is expressed directly in XPath. Instead of writing imperative crawl loops, wxpath lets you describe what to follow and what to extract in a single expression. **wxpath** executes that expression concurrently, breadth-first-*ish*, and streams results as they are discovered.
 
-By introducing the `url(...)` operator and the `///` syntax, wxpath's engine is able to perform deep (or paginated) web crawling and extraction.
+This expression fetches a page, extracts links, and streams them concurrently - no crawl loop required:
+
+```python
+import wxpath
+
+expr = "url('https://quotes.toscrape.com')//a/@href"
+
+for link in wxpath.wxpath_async_blocking_iter(expr):
+    print(link)
+```
+
+
+By introducing the `url(...)` operator and the `///` syntax, wxpath's engine is able to perform recursive (or paginated) web crawling and extraction:
+
+```python
+import wxpath
+
+path_expr = """
+url('https://quotes.toscrape.com')
+  ///url(//a/@href)
+    //a/@href
+"""
+
+for item in wxpath.wxpath_async_blocking_iter(path_expr, max_depth=1):
+    print(item)
+```
+
+
+## Why wxpath?
+
+Most web scrapers force you to write crawl control flow first, and extraction second.
+
+**wxpath** converges those two steps into one:
+- **You describe traversal declaratively**
+- **Extraction is expressed inline**
+- **The engine handles scheduling, concurrency, and deduplication**
+
+
+### RAG-Ready Output 
+
+Extract clean, structured JSON hierarchies directly from the graph - feed your LLMs signal, not noise. Refer to [LangChain Integration](https://rodricios.github.io/wxpath/api/integrations/langchain/) for more details.
+
 
-NOTE: This project is in early development. Core concepts are stable, but the API and features may change. Please report issues - in particular, deadlocked crawls or unexpected behavior - and any features you'd like to see (no guarantee they'll be implemented).
+### Deterministic
 
+**wxpath** is deterministic (read: not powered by LLMs). While we can't guarantee the network is stable, we can guarantee the traversal is.
+
+## Documentation (WIP)
+
+Documentation is now available [here](https://rodricios.github.io/wxpath/).
 
 ## Contents
 
-- [Example](#example)
+- [Example: Knowledge Graph](#example)
 - [Language Design](DESIGN.md)
 - [`url(...)` and `///url(...)` Explained](#url-and-url-explained)
 - [General flow](#general-flow)
@@ -47,6 +137,7 @@ NOTE: This project is in early development. Core concepts are stable, but the AP
 - [XPath 3.1](#xpath-31-by-default)
 - [Progress Bar](#progress-bar)
 - [CLI](#cli)
+- [TUI](#tui)
 - [Persistence and Caching](#persistence-and-caching)
 - [Settings](#settings)
 - [Hooks (Experimental)](#hooks-experimental)
@@ -56,7 +147,7 @@ NOTE: This project is in early development. Core concepts are stable, but the AP
 - [Advanced: Engine & Crawler Configuration](#advanced-engine--crawler-configuration)
 - [Project Philosophy](#project-philosophy)
 - [Warnings](#warnings)
-- [Commercial support / consulting](#commercial-support--consulting)
+- [Commercial support/consulting](#commercial-supportconsulting)
 - [Versioning](#versioning)
 - [License](#license)
 
@@ -73,7 +164,11 @@ CRAWLER_SETTINGS.headers = {'User-Agent': 'my-app/0.4.0 (contact: you@example.co
 # Crawl, extract fields, build a knowledge graph
 path_expr = """
 url('https://en.wikipedia.org/wiki/Expression_language')
-  ///url(//main//a/@href[starts-with(., '/wiki/') and not(contains(., ':'))])
+  ///url(
+        //main//a/@href[
+            starts-with(., '/wiki/') and not(contains(., ':'))
+        ]
+    )
     /map{
         'title': (//span[contains(@class, "mw-page-title-main")]/text())[1] ! string(.),
         'url': string(base-uri(.)),
@@ -86,15 +181,6 @@ for item in wxpath.wxpath_async_blocking_iter(path_expr, max_depth=1):
     print(item)
 ```
 
-Output:
-
-```python
-map{'title': 'Computer language', 'url': 'https://en.wikipedia.org/wiki/Computer_language', 'short_description': 'Formal language for communicating with a computer', 'forward_links': ['/wiki/Formal_language', '/wiki/Communication', ...]}
-map{'title': 'Advanced Boolean Expression Language', 'url': 'https://en.wikipedia.org/wiki/Advanced_Boolean_Expression_Language', 'short_description': 'Hardware description language and software', 'forward_links': ['/wiki/File:ABEL_HDL_example_SN74162.png', '/wiki/Hardware_description_language', ...]}
-map{'title': 'Machine-readable medium and data', 'url': 'https://en.wikipedia.org/wiki/Machine_readable', 'short_description': 'Medium capable of storing data in a format readable by a machine', 'forward_links': ['/wiki/File:EAN-13-ISBN-13.svg', '/wiki/ISBN', ...]}
-...
-```
-
 **Note:** Some sites (including Wikipedia) may block requests without proper headers.  
 See [Advanced: Engine & Crawler Configuration](#advanced-engine--crawler-configuration) to set a custom `User-Agent`.
 
@@ -266,12 +352,17 @@ Command line options:
 --cache                [true|false] (Default: False) Persist crawl results to a local database
 ```
 
+## TUI
+
+**wxpath** provides a terminal interface (TUI) for interactive expression testing and data extraction.
+
+See [TUI Quickstart](https://rodricios.github.io/wxpath/tui/quickstart.md) for more details.
 
 ## Persistence and Caching
 
 **wxpath** optionally persists crawl results to a local database. This is especially useful when you're crawling a large number of URLs, and you decide to pause the crawl, change extraction expressions, or otherwise need to restart the crawl. 
 
-**wxpath** supports two backends: sqlite and redis. SQLite is great for small-scale crawls, with a single worker (i.e., `engine.crawler.concurrency == 1`). Redis is great for large-scale crawls, with multiple workers. You will be encounter a warning if you `min(engine.crawler.concurrency, engine.crawler.per_host) > 1` when using the sqlite backend.
+**wxpath** supports two backends: sqlite and redis. SQLite is great for small-scale crawls, with a single worker (i.e., `engine.crawler.concurrency == 1`). Redis is great for large-scale crawls, with multiple workers. You will encounter a warning if `min(engine.crawler.concurrency, engine.crawler.per_host) > 1` when using the sqlite backend.
 
 To use, you must install the appropriate optional dependency:
 
@@ -406,6 +497,17 @@ path_expr = "url('https://en.wikipedia.org/wiki/Expression_language')//url(//mai
 items = list(wxpath_async_blocking_iter(path_expr, max_depth=1, engine=engine))
 ```
 
+### Runtime API (`wxpath_async*`) options
+
+- `max_depth`: int = 1
+- `progress`: bool = False
+- `engine`: WXPathEngine | None = None
+- `yield_errors`: bool = False
+
+
+### Settings
+You can also use [settings.py](src/wxpath/settings.py) to enable caching, throttling, concurrency and more.
+
 
 ## Project Philosophy
 
@@ -433,13 +535,15 @@ The following features are not yet supported:
 
 ## WARNINGS!!!
 
+This project is in early development. Core concepts are stable, but the API and features may change. Please report issues - in particular, deadlocked crawls or unexpected behavior - and any features you'd like to see (no guarantee they'll be implemented).
+
 - Be respectful when crawling websites. A scrapy-inspired throttler is enabled by default.
 - Deep crawls (`///`) require user discipline to avoid unbounded expansion (traversal explosion).
 - Deadlocks and hangs are possible in certain situations (e.g., all tasks waiting on blocked requests). Please report issues if you encounter such behavior.
 - Consider using timeouts, `max_depth`, and XPath predicates and filters to limit crawl scope.
 
 
-## Commercial support / consulting
+## Commercial support/consulting
 
 If you want help building or operating crawlers/data feeds with wxpath (extraction, scheduling, monitoring, breakage fixes) or other web-scraping needs, please contact me at: rodrigopala91@gmail.com.
 

wxpath-0.5.0.dist-info/RECORD

@@ -0,0 +1,44 @@
+wxpath/__init__.py,sha256=nKo2ggHdlNUhTPzZlPOW-XssyYjVar6XcqaFsZLxsKU,304
+wxpath/cli.py,sha256=P2MU6UzWHiN-5roo-GdEb4OpTlCp0XA3AlFmjL7fI1o,4544
+wxpath/patches.py,sha256=nNFpNuapF30aVMVz6K1iJDX2RWmiyiECx2_UprcwiT4,8417
+wxpath/settings.py,sha256=dBSIxVPlcsP3IYuhuHG0uxZaNXLzcNUdBxEaZsZHcAc,3862
+wxpath/tui.py,sha256=CG8xvGnYNbruD4lw50Agu8RKKUJEpEl0WG0SyLBW4c8,42786
+wxpath/tui_settings.py,sha256=rM2IBeOzQUIzjk2Ds1Jlnvb7IUtdJdKMN2j3GHk7Z9M,5051
+wxpath/core/__init__.py,sha256=U9_In2iRaZrpiIVavIli1M59gCB6Kn1en-1Fza-qIiI,257
+wxpath/core/dom.py,sha256=X0L3n8jRfO5evEypDaJTD-NQ3cLXWvnEUVERAHo3vV0,701
+wxpath/core/models.py,sha256=xsNY9ZmUILB5_O1GHRkn3cLBtPs3-krguU5NlqFe0bM,1664
+wxpath/core/ops.py,sha256=4vzLOqRM_LbXc1cAnWCuKGt2m_pbvyHO0p5ee2Upjog,9569
+wxpath/core/parser.py,sha256=ufUSEfyR6aO10pV_E39-uSiLQfYvngNQnHcs1GJlpbA,21392
+wxpath/core/runtime/__init__.py,sha256=_iCgkIWxXvxzQcenHOsjYGsk74HboTIYWOtgM8GtCyc,86
+wxpath/core/runtime/engine.py,sha256=ocGBTIHdFgOh3LzkgEUKZ59Ozn3nKqvBBAloj4Ln5D4,19229
+wxpath/core/runtime/helpers.py,sha256=RFLonAjRsL_CHFV0biUsgk0lOL8MKvHXdFg7p65xEP8,1554
+wxpath/hooks/__init__.py,sha256=9JG63e4z_8CZLWugFcY786hebaEEPZ5FmZhyDHat-98,294
+wxpath/hooks/builtin.py,sha256=GJ4w1C9djWNzAmAA3U0qI9OoCOeC5R8tEGtWXJVHSYs,4125
+wxpath/hooks/registry.py,sha256=-D11f_mMboeVAH8qsTkbKTQ0aGNaQ7F6zbXDsOIYxN0,4513
+wxpath/http/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wxpath/http/stats.py,sha256=aqZWuybc5RCv-AmKdNbEX4uw1YvZtFoE6591UfukZns,3319
+wxpath/http/client/__init__.py,sha256=9z_BWpU6gd-eTpoxIygsZZ84LJPZ1SnIlyL9SfzZ1as,203
+wxpath/http/client/cache.py,sha256=cHS4XlfOStoHTG83ypNITk3Oc0lqGoTRqV0_UWBWQFY,1811
+wxpath/http/client/crawler.py,sha256=-uRMhMV3_dYW9oxKEsvaVMDmglBuZC23EhuppWQbDkw,12579
+wxpath/http/client/request.py,sha256=cpqo_ASG_wKz0q6m33lsE0kIIthfANt8fx7ptxlyehY,1057
+wxpath/http/client/response.py,sha256=gvl7_2jITF1EUrUD6HLq7G6R7GLF0DxGeuHTznFK1hc,487
+wxpath/http/policy/backoff.py,sha256=NwdUR6bRe1RtUGSJOktj-p8IyC1l9xu_-Aa_Gj_u5sw,321
+wxpath/http/policy/retry.py,sha256=jx5t2OdnHsDzuYH120N6sc1RDZDfQD1OE7RCgLD9tAo,966
+wxpath/http/policy/robots.py,sha256=vllXX9me78YB6yrDdpH_bwyuR5QoC9uveGEl8PmHM9Q,3134
+wxpath/http/policy/throttler.py,sha256=wydMFV-0mxpHSI5iYkLfE78oY4z_fF8jW9MqCeb8G54,3014
+wxpath/integrations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wxpath/integrations/langchain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wxpath/integrations/langchain/loader.py,sha256=Iio4Fv03dYzNCFmaGl2pzmjR72QBziTcpfX4BtnoiZI,1907
+wxpath/integrations/langchain/examples/basic_rag.py,sha256=10V7-HjyRYqEE4S11S2HpjNwKfwi93rUbyFGco0AM04,2957
+wxpath/integrations/langchain/examples/rolling_window_rag.py,sha256=fKoOQNy4RjtCHj6N5dTd3AjrWutmLmoRSblK0VBD33Q,8174
+wxpath/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+wxpath/util/cleaners.py,sha256=JtUwCKjSJV-qw2CBrcB1oYswBDeXiqndGiz3-MlxeG0,946
+wxpath/util/common_paths.py,sha256=Y-0yq6IMjlSl1t4GbmK9TeJFTQ-MVvJOINhglvD4djA,980
+wxpath/util/logging.py,sha256=hgN4OC1y2oZWewtL-O-Ei_1lOaadH9eSyo0Iz2t_s1c,2858
+wxpath/util/serialize.py,sha256=uUs4C9VErpFd97smBM2bRWo2nW25kCgKdsMrVtVxhg8,575
+wxpath-0.5.0.dist-info/licenses/LICENSE,sha256=AVBZLhdWmqxm-f-dy5prVB1E-solHWoP2EXEIV_o-00,1076
+wxpath-0.5.0.dist-info/METADATA,sha256=uBaoDrnCdTvzmt3yZ2ywCImWCeg_zOTQKPIgDMA3LI4,22002
+wxpath-0.5.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+wxpath-0.5.0.dist-info/entry_points.txt,sha256=CSr67nPxU_tZ_XdAdDmvW9b9VRUhFAhGhEC41YNJEfE,72
+wxpath-0.5.0.dist-info/top_level.txt,sha256=uFCcveG78mnefxRGvYsR2OexDlKR_Z1UD4vZijUcex8,7
+wxpath-0.5.0.dist-info/RECORD,,

{wxpath-0.4.0.dist-info → wxpath-0.5.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{wxpath-0.4.0.dist-info → wxpath-0.5.0.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 wxpath = wxpath.cli:main
+wxpath-tui = wxpath.tui:main

wxpath-0.4.0.dist-info/RECORD

@@ -1,35 +0,0 @@
-wxpath/__init__.py,sha256=w1hFE_VSIYq_TSFLoPfp6MJbG1sA6BeChX6PYsXIK4o,265
-wxpath/cli.py,sha256=e0-mHkpuC1B_WyJw7wH43UBmtuF8oL8phQ4GEzUX0Ns,4332
-wxpath/patches.py,sha256=u0dOL-K-gvdO9SJvzGrqR9Zou6XduWjl6R7mzIcZtJg,2130
-wxpath/settings.py,sha256=a4TlCAOvmO03oOXiiYQzIDBMZU0XpTqntwnjVsumnas,3809
-wxpath/core/__init__.py,sha256=U9_In2iRaZrpiIVavIli1M59gCB6Kn1en-1Fza-qIiI,257
-wxpath/core/dom.py,sha256=X0L3n8jRfO5evEypDaJTD-NQ3cLXWvnEUVERAHo3vV0,701
-wxpath/core/models.py,sha256=3KYt-UwfLY2FlSRUHeA_getnYaNUMPW9wRrl2CRbPso,1611
-wxpath/core/ops.py,sha256=PTjX6c4QvCqGaByYYqaK4dte5iWO3lZzgqGrMXp6f6g,9727
-wxpath/core/parser.py,sha256=WfjQNixBz7nWtX2O0t19MOhUJmzGMg8Qol40P6oC8zc,18827
-wxpath/core/runtime/__init__.py,sha256=_iCgkIWxXvxzQcenHOsjYGsk74HboTIYWOtgM8GtCyc,86
-wxpath/core/runtime/engine.py,sha256=otCr2bGtw3MczuQxL-UKti_mnjvYVgHplVFcS_nDopo,15850
-wxpath/core/runtime/helpers.py,sha256=M1i4BryCktAxeboa4LOXMTNiKVCJLDBD-KpWCQXadpw,1434
-wxpath/hooks/__init__.py,sha256=9JG63e4z_8CZLWugFcY786hebaEEPZ5FmZhyDHat-98,294
-wxpath/hooks/builtin.py,sha256=GJ4w1C9djWNzAmAA3U0qI9OoCOeC5R8tEGtWXJVHSYs,4125
-wxpath/hooks/registry.py,sha256=-D11f_mMboeVAH8qsTkbKTQ0aGNaQ7F6zbXDsOIYxN0,4513
-wxpath/http/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wxpath/http/stats.py,sha256=aqZWuybc5RCv-AmKdNbEX4uw1YvZtFoE6591UfukZns,3319
-wxpath/http/client/__init__.py,sha256=QpdmqzcznUeuFvT3IIo-LmBUUHEa2BDq9sHGAHJnDLI,202
-wxpath/http/client/cache.py,sha256=cHS4XlfOStoHTG83ypNITk3Oc0lqGoTRqV0_UWBWQFY,1811
-wxpath/http/client/crawler.py,sha256=ZbMXgs9CemYafKkAwbLfcOoT6LLdDsbmPwMH8jWzAAg,12159
-wxpath/http/client/request.py,sha256=LF_OIXetfouyE5GwEqp0cya0oMAZouKRPNFRFGscQS8,1050
-wxpath/http/client/response.py,sha256=z9LQPnDN-NZRnQpIKozaWCqgpRejc6nixCr_XaPyqUQ,334
-wxpath/http/policy/backoff.py,sha256=NwdUR6bRe1RtUGSJOktj-p8IyC1l9xu_-Aa_Gj_u5sw,321
-wxpath/http/policy/retry.py,sha256=WSrQfCy1F7IcXFpVGDi4HTphNhFq12p4DaMO0_4dgrw,982
-wxpath/http/policy/robots.py,sha256=vllXX9me78YB6yrDdpH_bwyuR5QoC9uveGEl8PmHM9Q,3134
-wxpath/http/policy/throttler.py,sha256=wydMFV-0mxpHSI5iYkLfE78oY4z_fF8jW9MqCeb8G54,3014
-wxpath/util/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wxpath/util/logging.py,sha256=oQi8sp7yKWgXkkcJ4U4WHp7TyBCQiK4VhSXOSb8pGw0,2965
-wxpath/util/serialize.py,sha256=uUs4C9VErpFd97smBM2bRWo2nW25kCgKdsMrVtVxhg8,575
-wxpath-0.4.0.dist-info/licenses/LICENSE,sha256=AVBZLhdWmqxm-f-dy5prVB1E-solHWoP2EXEIV_o-00,1076
-wxpath-0.4.0.dist-info/METADATA,sha256=1iEqBwgUjNcZaupy5WinzJkm5DKzHUMnSG27w4gbWvg,19233
-wxpath-0.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-wxpath-0.4.0.dist-info/entry_points.txt,sha256=FwoIOnUTl-DjPqVw-eb9EHHiiXCyRZy_mEQKFu2eb5Y,43
-wxpath-0.4.0.dist-info/top_level.txt,sha256=uFCcveG78mnefxRGvYsR2OexDlKR_Z1UD4vZijUcex8,7
-wxpath-0.4.0.dist-info/RECORD,,