urban-json-html 0.1.0__py3-none-any.whl

urban_json_html/__init__.py

@@ -0,0 +1,166 @@
+"""Plugin urban-json : conversion HTML vers JSON (``loadhtml``).
+
+Port de ``ServiceHtml`` / ``HtmlToJson`` (.NET, HtmlAgilityPack) avec le
+``html.parser`` de la bibliothèque standard, sans dépendance. Forme produite,
+identique au .NET :
+
+* élément -> ``{"#id": balise, <attributs>…, "content": enfant | [enfants]}``
+  (``content`` absent sans enfant, valeur seule pour un enfant unique) ;
+* texte -> ``"#text: <texte brut>"``, ignoré s'il n'est fait que de blancs ;
+* commentaire et ``<!DOCTYPE>`` -> ``"#comment: <!-- … -->"`` (HtmlAgilityPack
+  range la déclaration DOCTYPE parmi les commentaires) ;
+* racine -> ``{"#id": "#document", …}``.
+
+Comme HtmlAgilityPack, le texte garde ses entités telles quelles (``&amp;``) et
+la casse d'origine des balises est conservée. Écarts : les noms d'attributs sont
+mis en minuscules et leurs valeurs décodées (``html.parser`` le fait toujours) ;
+un chemin relatif est accepté (le .NET exigeait un chemin absolu ou une URI).
+
+Découvert automatiquement via l'entry point ``urban_json.functions``.
+"""
+
+from __future__ import annotations
+
+import os
+import re
+from html.parser import HTMLParser
+from typing import Any
+from urllib.parse import unquote, urlparse
+
+from urban_json import JsltError
+
+__version__ = "0.1.0"
+
+__all__ = ["execute_loadhtml", "html_to_json", "register"]
+
+#: Délai maximal (secondes) pour charger une page distante.
+DEFAULT_TIMEOUT = 30.0
+
+# Éléments HTML sans contenu ni balise fermante.
+_VOID = {
+    "area", "base", "br", "col", "embed", "hr", "img", "input", "link", "meta",
+    "param", "source", "track", "wbr",
+}
+_TAG_NAME = re.compile(r"<\s*([^\s/>]+)")
+
+
+class _Node:
+    __slots__ = ("attrs", "children", "name")
+
+    def __init__(self, name: str, attrs: list[tuple[str, str | None]]) -> None:
+        self.name = name
+        self.attrs = attrs
+        self.children: list[Any] = []
+
+
+class _TreeBuilder(HTMLParser):
+    def __init__(self) -> None:
+        super().__init__(convert_charrefs=False)
+        self.root = _Node("#document", [])
+        self.stack = [self.root]
+
+    def _append(self, item: Any) -> None:
+        self.stack[-1].children.append(item)
+
+    def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
+        raw = self.get_starttag_text() or ""
+        match = _TAG_NAME.match(raw)
+        node = _Node(match.group(1) if match else tag, attrs)
+        self._append(node)
+        if tag not in _VOID:
+            self.stack.append(node)
+
+    def handle_startendtag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
+        raw = self.get_starttag_text() or ""
+        match = _TAG_NAME.match(raw)
+        self._append(_Node(match.group(1) if match else tag, attrs))
+
+    def handle_endtag(self, tag: str) -> None:
+        # Ferme jusqu'à la balise ouverte correspondante ; une fermante orpheline est ignorée.
+        for depth in range(len(self.stack) - 1, 0, -1):
+            if self.stack[depth].name.lower() == tag:
+                del self.stack[depth:]
+                return
+
+    def handle_data(self, data: str) -> None:
+        self._append(("#text", data))
+
+    def handle_entityref(self, name: str) -> None:
+        self._append(("#text", f"&{name};"))
+
+    def handle_charref(self, name: str) -> None:
+        self._append(("#text", f"&#{name};"))
+
+    def handle_comment(self, data: str) -> None:
+        self._append(("#comment", f"<!--{data}-->"))
+
+    def handle_decl(self, decl: str) -> None:
+        self._append(("#comment", f"<!{decl}>"))
+
+
+def _merge_text(children: list[Any]) -> list[Any]:
+    """Recolle les morceaux de texte consécutifs (le parseur coupe sur les entités)."""
+    merged: list[Any] = []
+    for child in children:
+        if isinstance(child, tuple) and child[0] == "#text" and merged and isinstance(merged[-1], tuple) \
+                and merged[-1][0] == "#text":
+            merged[-1] = ("#text", merged[-1][1] + child[1])
+        else:
+            merged.append(child)
+    return merged
+
+
+def _to_json(item: Any) -> Any:
+    if isinstance(item, tuple):
+        kind, text = item
+        return f"{kind}: {text}" if text.strip() else None
+    result: dict[str, Any] = {"#id": item.name}
+    for name, value in item.attrs:
+        result.setdefault(name, value if value is not None else "")
+    children = [c for c in (_to_json(child) for child in _merge_text(item.children)) if c is not None]
+    if len(children) == 1:
+        result["content"] = children[0]
+    elif children:
+        result["content"] = children
+    return result
+
+
+def html_to_json(payload: str) -> dict:
+    """Convertit un texte HTML en JSON (forme ``HtmlToJson`` du .NET)."""
+    builder = _TreeBuilder()
+    builder.feed(payload)
+    builder.close()
+    return _to_json(builder.root)
+
+
+def _fetch_url(url: str) -> str:
+    """Charge une page distante. Point d'injection pour les tests."""
+    from urllib.request import Request, urlopen
+
+    request = Request(url, headers={"User-Agent": "urban-json-html"})
+    with urlopen(request, timeout=DEFAULT_TIMEOUT) as response:
+        charset = response.headers.get_content_charset() or "utf-8"
+        return response.read().decode(charset, errors="replace")
+
+
+def execute_loadhtml(ctx: Any, path: Any = None) -> dict:
+    if not path:
+        raise JsltError("loadhtml : le chemin ou l'URL de la page est requis")
+    location = str(path)
+    parsed = urlparse(location)
+    if parsed.scheme in ("http", "https"):
+        return html_to_json(_fetch_url(location))
+    file_path = unquote(parsed.path) if parsed.scheme == "file" else location
+    if not os.path.isfile(file_path):
+        raise JsltError(f"loadhtml : page HTML introuvable {file_path!r}")
+    with open(file_path, encoding="utf-8-sig", errors="replace") as handle:
+        return html_to_json(handle.read())
+
+
+def register(registry: Any) -> None:
+    """Enregistre ``loadhtml``."""
+    registry.register(
+        "loadhtml",
+        execute_loadhtml,
+        description="Charge une page HTML (fichier ou URL http/https) et la convertit en JSON {#id, attributs, content}",
+    )

urban_json_html-0.1.0.dist-info/METADATA

@@ -0,0 +1,49 @@
+Metadata-Version: 2.4
+Name: urban-json-html
+Version: 0.1.0
+Summary: Plugin urban-json : conversion HTML vers JSON (loadhtml).
+Author-email: Gael Beard <gaelgael5@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/gaelgael5/Jslt
+Project-URL: Repository, https://github.com/gaelgael5/Jslt
+Keywords: json,transform,template,jslt,html,plugin
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Markup
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: urban-json
+Dynamic: license-file
+
+# urban-json-html
+
+Plugin [urban-json](https://github.com/gaelgael5/Jslt) : **HTML vers JSON** dans les
+templates, via `loadhtml(chemin_ou_url)` (port de `ServiceHtml`, .NET). Aucune
+dépendance : `html.parser` de la bibliothèque standard.
+
+```bash
+pip install urban-json-html
+```
+
+Forme produite (celle du .NET, HtmlAgilityPack) :
+
+```json
+{ "#id": "#document", "content": { "#id": "p", "class": "x", "content": "#text: Bonjour" } }
+```
+
+- élément → `{"#id": balise, attributs…, "content": enfant | [enfants]}` ;
+- texte → `"#text: …"` (blancs seuls ignorés, entités conservées) ;
+- commentaire et `<!DOCTYPE>` → `"#comment: …"`.
+
+`loadhtml` accepte un fichier (chemin ou URI `file://`) ou une URL `http(s)://`
+(délai de 30 s). Attention aux URL issues de données non fiables (SSRF).

urban_json_html-0.1.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+urban_json_html/__init__.py,sha256=h852DrxLxFgXTfOe9pQs33FvPiydiAE-o7_70roXygw,6067
+urban_json_html/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+urban_json_html-0.1.0.dist-info/licenses/LICENSE,sha256=LdXMQzg0w6hrGI_vhgHsmOLKcHTkyF5PyUXkP9fV7mA,1068
+urban_json_html-0.1.0.dist-info/METADATA,sha256=fcaOTEGXp3QQdAK2DAcuoZZPeA4-TjIJ33RMlCRiIK8,1895
+urban_json_html-0.1.0.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+urban_json_html-0.1.0.dist-info/entry_points.txt,sha256=kfvs9-zAVUnPvaTugeaugRlEvYvu0TIS_l9npgkEDLo,55
+urban_json_html-0.1.0.dist-info/top_level.txt,sha256=eQgfMqtQtQnDLz6zKVK9JZVEZ0uS6jrJd4a8ytJ-lCk,16
+urban_json_html-0.1.0.dist-info/RECORD,,

urban_json_html-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.2.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

urban_json_html-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[urban_json.functions]
+html = urban_json_html:register

urban_json_html-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 black beard
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

urban_json_html-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+urban_json_html