Issue #32 cleanup — drop the last 5 mis-oriented vocab pairs

Two small fixes after the LLM-vision pass:

1. merge_pdf_into_book.py — when the LLM classifies an image as 'hybrid'
   but extracts zero pairs (e.g., a conjugation table whose only English
   text is on the section header that was excluded by the prompt rules),
   respect that decision instead of falling through to the bbox/heuristic
   pipeline. Previously: 1 chapter-2 estar conjugation table generated
   4 bad pairs from the heuristic fallback.

2. fix_vocab.py language_score — recognize Spanish present-perfect
   ('he tenido', 'He andado por este pueblo') as Spanish. The classifier
   was treating the auxiliary 'he'/'has'/'ha' as English subject pronouns,
   producing false-positive mis-orientation flags on 4 chapter-15/20/23
   present-perfect example tables.

Result: mis-oriented vocab pairs across the book go from 5 → 0.
textbookDataVersion bumped to 14.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Conjuga/Conjuga/Services/DataLoader.swift

@@ -6,7 +6,7 @@ actor DataLoader {
     static let courseDataVersion = 7
     static let courseDataKey = "courseDataVersion"
 
-    static let textbookDataVersion = 13
+    static let textbookDataVersion = 14
     static let textbookDataKey = "textbookDataVersion"
 
     /// Quick check: does the DB need seeding or course data refresh?

Conjuga/Conjuga/textbook_vocab.json

@@ -1297,78 +1297,6 @@
           "section": "Subject Pronouns",
           "sourceImage": "f0014-01.jpg"
         },
-        {
-          "front": "vosotros estáis",
-          "back": "he is",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0015-01.jpg"
-        },
-        {
-          "front": "ellos están",
-          "back": "she is",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0015-01.jpg"
-        },
-        {
-          "front": "ellas están",
-          "back": "you are",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0015-01.jpg"
-        },
-        {
-          "front": "Uds. están",
-          "back": "nosotros estamos",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0015-01.jpg"
-        },
-        {
-          "front": "La comida está buena.",
-          "back": "The meal is (tastes) good.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0016-02.jpg"
-        },
-        {
-          "front": "El pescado está delicioso.",
-          "back": "The fish is (tastes) delicious.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0016-02.jpg"
-        },
-        {
-          "front": "La sopa está sabrosa.",
-          "back": "The soup is (tastes) delicious",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0016-02.jpg"
-        },
-        {
-          "front": "Ella está hermosa hoy.",
-          "back": "She is (looks) pretty today.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0016-02.jpg"
-        },
-        {
-          "front": "Él está guapo.",
-          "back": "He is (looks) handsome.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Estar (to be)",
-          "sourceImage": "f0016-02.jpg"
-        },
         {
           "front": "¿cómo?",
           "back": "how?",
@@ -1513,150 +1441,6 @@
           "section": "Adjectives",
           "sourceImage": "f0017-03.jpg"
         },
-        {
-          "front": "La casa es roja.",
-          "back": "The house is red.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0019-02.jpg"
-        },
-        {
-          "front": "El libro es azul.",
-          "back": "The book is blue.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0019-02.jpg"
-        },
-        {
-          "front": "Los carros son viejos.",
-          "back": "The cars are old.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0019-02.jpg"
-        },
-        {
-          "front": "Somos simpáticos.",
-          "back": "We are nice.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0019-02.jpg"
-        },
-        {
-          "front": "¿ Es la flor amarilla?",
-          "back": "Is the flower yellow?",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0019-02.jpg"
-        },
-        {
-          "front": "El vino es de Portugal.",
-          "back": "The wine is from Portugal",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-01.jpg"
-        },
-        {
-          "front": "La cerveza es de México.",
-          "back": "The beer is from Mexico.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-01.jpg"
-        },
-        {
-          "front": "El café es de Brazil.",
-          "back": "The coffee is from Brazil.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-01.jpg"
-        },
-        {
-          "front": "Somos amigos.",
-          "back": "We are friends.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-02.jpg"
-        },
-        {
-          "front": "José y Eduardo son hermanos.",
-          "back": "Joe and Ed are brothers",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-02.jpg"
-        },
-        {
-          "front": "Pablo es español.",
-          "back": "Paul is Spanish.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-02.jpg"
-        },
-        {
-          "front": "¿ Eres tú cubano?",
-          "back": "Are you Cuban?",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-02.jpg"
-        },
-        {
-          "front": "Fila es católica.",
-          "back": "She is Catholic",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-02.jpg"
-        },
-        {
-          "front": "La mesa es de madera.",
-          "back": "The table is of wood.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-03.jpg"
-        },
-        {
-          "front": "La bolsa es de plástico.",
-          "back": "The bag is of plastic.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-03.jpg"
-        },
-        {
-          "front": "Los zapatos son de cuero.",
-          "back": "The shoes are of leather:",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-03.jpg"
-        },
-        {
-          "front": "Las ventanas son de vidrio.",
-          "back": "The windows are of glass",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-03.jpg"
-        },
-        {
-          "front": "La casa es de piedra.",
-          "back": "The house is of stone.",
-          "chapter": 2,
-          "chapterTitle": "Estar, Ser, and Subject Pronouns",
-          "section": "Ser (to be)",
-          "sourceImage": "f0020-03.jpg"
-        },
         {
           "front": "la alcoba",
           "back": "the bedroom",

Conjuga/Scripts/textbook/fix_vocab.py

@@ -46,6 +46,9 @@ SPANISH_ARTICLES = {"el", "la", "los", "las", "un", "una", "unos", "unas"}
 ENGLISH_STARTERS = {"the", "a", "an", "to", "my", "his", "her", "our", "their"}
 
 
+HABER_FORMS = {"he", "has", "ha", "hemos", "habéis", "han"}
+
+
 def language_score(s: str) -> "tuple[int, int]":
     """Return (es_score, en_score) for a string."""
     es = 0
@@ -56,9 +59,17 @@ def language_score(s: str) -> "tuple[int, int]":
     if not words:
         return (es, en)
     first = words[0].strip(",.;:")
-    if first in SPANISH_ARTICLES:
+    second = words[1].strip(",.;:") if len(words) > 1 else ""
+    # Spanish present-perfect ("he tenido", "Ha andado") starts with a haber
+    # form followed by an -ado/-ido past participle. Recognise this pattern
+    # before the bare-pronoun check so "he" isn't mistaken for English "he".
+    if first in HABER_FORMS and (
+        second.endswith(("ado", "ido", "to", "cho", "sto", "esto"))
+    ):
+        es += 3
+    elif first in SPANISH_ARTICLES:
         es += 2
-    if first in ENGLISH_STARTERS:
+    elif first in ENGLISH_STARTERS:
         en += 2
     # Spanish-likely endings on later words
     for w in words:

Conjuga/Scripts/textbook/merge_pdf_into_book.py

@@ -307,10 +307,13 @@ def main() -> None:
 
                 # Choose pair source. For reference_only (Spanish-only tables)
                 # we deliberately produce no cards — the UI will fall back to
-                # rendering the flat OCR lines as a reference list.
+                # rendering the flat OCR lines as a reference list. Same for
-                if llm_kind == "reference_only":
+                # hybrid images where the LLM determined no genuine pair rows
+                # exist (e.g. estar conjugations with English glosses on the
+                # header row only).
+                if llm_kind == "reference_only" or (llm_kind == "hybrid" and not llm_pairs):
                     cards_for_block = []
-                    pair_source = "llm-reference"
+                    pair_source = "llm-no-pairs"
                 elif llm_pairs:
                     cards_for_block = [
                         {"front": p["es"], "back": p["en"]}