Merge pull request #12 from migatu/feat/noise-and-abbrev

Odsiewanie szumu + rozwijanie skrótów sygnifikatorów

services/logic/app/abbreviations.py

@@ -0,0 +1,58 @@
+"""Rozwijanie skrótów sygnifikatorów do postaci czytelnej (na bazie SIGNIFICATORS KEY).
+
+W bazie zapis jest skrótowy z prefiksem `[` (np. `[Su in [Tau`, `[Sa [conj [Su in 6th H.`).
+Ten moduł zamienia go na tekst czytelny: „Sun in Taurus", „Saturn conjunction Sun
+in 6th house". Słownik pochodzi z pliku SIGNIFICATORS KEY (mały, stabilny — wpięty
+jako built-in; można rozszerzać).
+"""
+from __future__ import annotations
+
+import re
+
+# skrót (bez nawiasu) -> pełna nazwa
+ABBREVIATIONS: dict[str, str] = {
+    # znaki zodiaku
+    "Ari": "Aries", "Tau": "Taurus", "Gem": "Gemini", "Can": "Cancer",
+    "Leo": "Leo", "Vir": "Virgo", "Lib": "Libra", "Sco": "Scorpio",
+    "Sag": "Sagittarius", "Cap": "Capricorn", "Aqu": "Aquarius", "Pis": "Pisces",
+    # planety klasyczne + światła
+    "Su": "Sun", "Mo": "Moon", "Me": "Mercury", "Ve": "Venus",
+    "Ma": "Mars", "Ju": "Jupiter", "Sa": "Saturn",
+    # planety nowożytne
+    "Ur": "Uranus", "Ne": "Neptune", "Pl": "Pluto",
+    # węzły i punkty
+    "NN": "North Node", "SN": "South Node", "Lilith": "Lilith", "Chiron": "Chiron",
+    # osie
+    "Asc": "Ascendant", "Dsc": "Descendant", "MC": "Midheaven", "IC": "Imum Coeli",
+    # aspekty
+    "conj": "conjunction", "sex": "sextile", "sq": "square", "tri": "trine",
+    "opp": "opposition", "semisex": "semisextile", "semisq": "semisquare",
+    "sesquisq": "sesquisquare", "quincunx": "quincunx", "asp": "aspect",
+    # domy jako tokeny [h1..[h12
+    **{f"h{i}": f"{i}th house" for i in range(1, 13)},
+    # ruch
+    "Rx": "retrograde", "R": "retrograde",
+}
+# poprawki nieregularnych liczebników domów
+ABBREVIATIONS.update({"h1": "1st house", "h2": "2nd house", "h3": "3rd house"})
+
+# rozwinięcia słów spoza składni `[`
+_WORDS = {
+    "affl.": "afflicted",
+    "P. Dec.": "parallel of declination",
+    "espec.": "especially",
+}
+
+_TOKEN = re.compile(r"\[([A-Za-z]+)")
+_HOUSE = re.compile(r"(\d+(?:st|nd|rd|th))\s*H\.", re.IGNORECASE)
+
+
+def expand(text: str) -> str:
+    """Zamienia skróty na pełne nazwy; nieznane tokeny zostawia bez nawiasu."""
+    if not text:
+        return text
+    out = _TOKEN.sub(lambda m: ABBREVIATIONS.get(m.group(1), m.group(1)), text)
+    out = _HOUSE.sub(lambda m: f"{m.group(1)} house", out)
+    for k, v in _WORDS.items():
+        out = out.replace(k, v)
+    return out

services/logic/app/significators.py

@@ -13,6 +13,7 @@ from __future__ import annotations
 
 from typing import Any, Protocol
 
+from app.abbreviations import expand
 from app.engine.formats import SIGN_ABBR, SIGNS
 
 PLANET_ABBR = {
@@ -38,11 +39,13 @@ def _effect(row: dict) -> str:
 
 def _is_noise(sig: str, effect: str) -> bool:
     s = sig.strip().lower()
+    e = effect.strip().lower()
     return (
-        not effect
-        or s.startswith("significator")
+        e in ("", "nan", "x", "x?", "?", "-")     # efekt pusty/zastępczy
+        or s.startswith("significator")            # wiersz-legenda/nagłówek
         or "header" in s
-        or s in ("x", "x?", "nan")
+        or s.startswith("*")                       # *MARKER / *header
+        or s in ("x", "x?", "nan")                 # znacznik „pomiń rekord"
     )
 
 
@@ -65,7 +68,7 @@ def _facet_samples(rows: list[dict], token: str, limit: int = 4) -> list[dict]:
         eff = _effect(r)
         if _is_noise(sig, eff):
             continue
-        out.append({"significator": sig.strip(), "effect": eff})
+        out.append({"significator": sig.strip(), "expanded": expand(sig.strip()), "effect": eff})
     return out
 
 

services/logic/tests/test_abbreviations.py

@@ -0,0 +1,22 @@
+"""Testy rozwijania skrótów sygnifikatorów."""
+from app.abbreviations import expand
+
+
+def test_planet_in_sign():
+    assert expand("[Su in [Tau") == "Sun in Taurus"
+
+
+def test_aspect_and_house():
+    assert expand("[Sa [conj [Su in 6th H.") == "Saturn conjunction Sun in 6th house"
+
+
+def test_affliction_word_and_house():
+    assert expand("[Ne affl. in the 7th H.") == "Neptune afflicted in the 7th house"
+
+
+def test_unknown_token_kept_without_bracket():
+    assert expand("[Xyz rising") == "Xyz rising"
+
+
+def test_empty_passthrough():
+    assert expand("") == ""

services/logic/tests/test_significators.py

@@ -25,6 +25,7 @@ def test_sign_and_house_facets():
     facets = {f["type"]: f for f in item["facets"]}
     assert facets["sign"]["count"] == 1
     assert facets["sign"]["samples"][0]["effect"] == "efekt znak"
+    assert facets["sign"]["samples"][0]["expanded"] == "Sun in Taurus"   # rozwinięcie skrótu
     assert facets["house"]["count"] == 1
     assert facets["house"]["token"] == "11th H."
     assert facets["house"]["samples"][0]["effect"] == "efekt dom"

services/presentation/app/static/styles.css

@@ -61,3 +61,4 @@ tr:last-child td { border-bottom: none; }
 .samples td.nowrap { color: var(--accent); padding-right: 1rem; }
 .facet { margin: .4rem 0 .6rem 1rem; }
 .facet-head { color: var(--ink); font-size: .9rem; }
+.samples td.sig { color: var(--accent); padding-right: 1rem; cursor: help; }

services/presentation/app/templates/interpret.html

@@ -56,7 +56,7 @@
             <table class="samples">
               <tbody>
                 {% for s in f.samples %}
-                  <tr><td class="mono nowrap">{{ s.significator }}</td><td>{{ s.effect }}</td></tr>
+                  <tr><td class="sig nowrap" title="{{ s.significator }}">{{ s.expanded }}</td><td>{{ s.effect }}</td></tr>
                 {% endfor %}
               </tbody>
             </table>