bulid 63

hockey_data/navigation_labels.py

@@ -0,0 +1,94 @@
+from __future__ import annotations
+
+from typing import Any
+from xml.etree import ElementTree as ET
+
+XML_LANG = "{http://www.w3.org/XML/1998/namespace}lang"
+
+
+def _text(value: Any) -> str:
+    return str(value or "").strip()
+
+
+def _labels(node: ET.Element) -> dict[str, dict[str, str]]:
+    result = {
+        "ru": {"label": "", "description": "", "short": ""},
+        "en": {"label": "", "description": "", "short": ""},
+    }
+    for label in node.findall("./label"):
+        language = _text(label.attrib.get(XML_LANG) or label.attrib.get("lang") or "ru").lower()
+        if language not in result:
+            continue
+        result[language] = {
+            "label": _text(label.text),
+            "description": _text(label.attrib.get("description")),
+            "short": _text(label.attrib.get("short")),
+        }
+    return result
+
+
+def _merge_entry(target: dict[str, Any], source: dict[str, Any]) -> None:
+    for language in ("ru", "en"):
+        current = target.setdefault(language, {"label": "", "description": "", "short": ""})
+        incoming = source.get(language, {})
+        for key in ("label", "description", "short"):
+            if not current.get(key) and incoming.get(key):
+                current[key] = incoming[key]
+
+
+def parse_navigation_labels_xml(content: bytes | str) -> dict[str, Any]:
+    raw = content.encode("utf-8") if isinstance(content, str) else content
+    root = ET.fromstring(raw)
+    columns: dict[str, dict[str, Any]] = {}
+    by_section: dict[str, dict[str, dict[str, Any]]] = {}
+    sections: dict[str, dict[str, Any]] = {}
+
+    for item in root.findall(".//list//item[@section]"):
+        section = _text(item.attrib.get("section"))
+        if section:
+            entry = _labels(item)
+            target = sections.setdefault(section, {})
+            _merge_entry(target, entry)
+
+    for columns_node in root.findall(".//columns"):
+        section_names = [part for part in _text(columns_node.attrib.get("sections")).split() if part]
+        for index, cell in enumerate(columns_node.findall("./cell")):
+            ref = _text(cell.attrib.get("ref"))
+            labels = _labels(cell)
+            if not ref:
+                ru = labels.get("ru", {}).get("label", "").casefold()
+                en = labels.get("en", {}).get("label", "").casefold()
+                if ru in {"игрок", "хоккеист"} or en == "player":
+                    ref = "player"
+                elif ru in {"клуб", "команда"} or en == "team":
+                    ref = "team"
+                elif ru == "№" or en in {"№", "no.", "number"}:
+                    ref = "number"
+                elif index == 0:
+                    ref = "rank"
+                else:
+                    continue
+            entry = {
+                **labels,
+                "datatype": _text(cell.attrib.get("datatype")),
+                "sortable": _text(cell.attrib.get("sortable")),
+                "default": _text(cell.attrib.get("default")),
+            }
+            global_entry = columns.setdefault(ref, {})
+            _merge_entry(global_entry, entry)
+            for key in ("datatype", "sortable", "default"):
+                if not global_entry.get(key) and entry.get(key):
+                    global_entry[key] = entry[key]
+            for section in section_names:
+                section_entry = by_section.setdefault(section, {}).setdefault(ref, {})
+                _merge_entry(section_entry, entry)
+                for key in ("datatype", "sortable", "default"):
+                    if not section_entry.get(key) and entry.get(key):
+                        section_entry[key] = entry[key]
+
+    return {
+        "available": bool(columns or sections),
+        "columns": columns,
+        "columns_by_section": by_section,
+        "sections": sections,
+    }