Liste les nouveaux personnages par année

README.md

@@ -245,6 +245,7 @@ Le script relit `data/intermediate/sets_enriched.csv`, `data/intermediate/parts_
 2. `python -m scripts.plot_minifig_characters`
 3. `python -m scripts.plot_minifig_character_variations`
 4. `python -m scripts.plot_minifig_new_characters`
+5. `python -m scripts.list_new_minifig_characters`
 
 Le premier script lit `data/intermediate/minifigs_by_set.csv`, compte le nombre de minifigs distinctes par personnage (`known_character` + `fig_num`), écrit `data/intermediate/minifig_characters_counts.csv`, puis trace `figures/step22/minifig_characters.png` (barres horizontales triées). Les barres sont colorées en fonction du genre renseigné dans `config/known_character_genders.csv`.
 
@@ -252,6 +253,8 @@ Le second script lit `data/intermediate/minifigs_by_set.csv`, exclut les figuran
 
 Le troisième script lit `data/intermediate/minifigs_by_set.csv` et `data/intermediate/sets_enriched.csv`, exclut les figurants, compte les nouveaux personnages introduits chaque année entre 2015 et 2025, sérialise `data/intermediate/minifig_new_characters_by_year.csv`, puis trace `figures/step23/minifig_new_characters_per_year.png` (barres avec jalons issus de `config/milestones.csv`).
 
+Le quatrième script lit `data/intermediate/minifigs_by_set.csv` et `data/intermediate/sets_enriched.csv`, exclut les figurants, liste pour chaque année (2015-2025) les personnages introduits et les sets de cette année contenant ces minifigs, puis produit `data/final/minifig_new_characters_by_year.csv` et `data/final/minifig_new_characters_by_year.md` (format markdown minimal pour le blog).
+
 ### Étape 23 : présence annuelle des personnages
 
 1. `source .venv/bin/activate`

lib/rebrickable/minifig_characters.py

@@ -110,6 +110,69 @@ def aggregate_new_characters_by_year(
     return results
 
 
+def aggregate_new_character_sets(
+    minifigs_rows: Iterable[dict],
+    sets_lookup: Dict[str, dict],
+    excluded_characters: Sequence[str] | None = None,
+    start_year: int | None = None,
+    end_year: int | None = None,
+) -> List[dict]:
+    """Liste les personnages introduits par année avec les sets correspondants."""
+    excluded = set(excluded_characters or [])
+    first_year: Dict[str, int] = {}
+    for row in minifigs_rows:
+        character = row["known_character"].strip()
+        fig_num = row["fig_num"].strip()
+        if character == "" or fig_num == "":
+            continue
+        if character in excluded:
+            continue
+        set_row = sets_lookup.get(row["set_num"])
+        if set_row is None:
+            continue
+        year_int = int(set_row["year"])
+        current = first_year.get(character)
+        if current is None or year_int < current:
+            first_year[character] = year_int
+    rows: List[dict] = []
+    seen: set[tuple[str, str]] = set()
+    for row in minifigs_rows:
+        character = row["known_character"].strip()
+        fig_num = row["fig_num"].strip()
+        if character == "" or fig_num == "":
+            continue
+        if character in excluded:
+            continue
+        set_row = sets_lookup.get(row["set_num"])
+        if set_row is None:
+            continue
+        intro_year = first_year.get(character)
+        if intro_year is None:
+            continue
+        if start_year is not None and intro_year < start_year:
+            continue
+        if end_year is not None and intro_year > end_year:
+            continue
+        if int(set_row["year"]) != intro_year:
+            continue
+        key = (character, set_row["set_num"])
+        if key in seen:
+            continue
+        rows.append(
+            {
+                "year": str(int(set_row["year"])),
+                "known_character": character,
+                "set_num": set_row["set_num"],
+                "set_id": set_row.get("set_id", ""),
+                "set_name": set_row.get("name", ""),
+                "rebrickable_url": set_row.get("rebrickable_url", ""),
+            }
+        )
+        seen.add(key)
+    rows.sort(key=lambda r: (int(r["year"]), r["known_character"], r["set_id"]))
+    return rows
+
+
 def aggregate_by_gender(rows: Iterable[dict]) -> List[dict]:
     """Compte les minifigs distinctes par genre (fig_num unique)."""
     genders_by_fig: Dict[str, str] = {}
@@ -154,6 +217,38 @@ def write_new_characters_by_year(path: Path, rows: Sequence[dict]) -> None:
             writer.writerow(row)
 
 
+def write_new_character_sets_csv(path: Path, rows: Sequence[dict]) -> None:
+    """Écrit le CSV listant les personnages introduits et leurs sets."""
+    ensure_parent_dir(path)
+    fieldnames = ["year", "known_character", "set_num", "set_id", "set_name", "rebrickable_url"]
+    with path.open("w", newline="") as csv_file:
+        writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
+        writer.writeheader()
+        for row in rows:
+            writer.writerow(row)
+
+
+def write_new_character_sets_markdown(path: Path, rows: Sequence[dict]) -> None:
+    """Écrit un Markdown listant les personnages introduits par année et leurs sets."""
+    ensure_parent_dir(path)
+    grouped: Dict[str, Dict[str, List[dict]]] = {}
+    for row in rows:
+        year_group = grouped.setdefault(row["year"], {})
+        characters = year_group.setdefault(row["known_character"], [])
+        characters.append(row)
+    with path.open("w") as md_file:
+        for year in sorted(grouped.keys(), key=int):
+            md_file.write(f"##### {year}\n\n")
+            for character in sorted(grouped[year].keys()):
+                md_file.write(f"- {character}\n")
+                for entry in sorted(grouped[year][character], key=lambda r: r["set_id"]):
+                    link = entry["rebrickable_url"] or ""
+                    set_id = entry["set_id"]
+                    name = entry["set_name"]
+                    md_file.write(f"    - [{set_id}]({link}) - {name}\n")
+            md_file.write("\n")
+
+
 def write_gender_counts(path: Path, rows: Sequence[dict]) -> None:
     """Écrit le CSV des comptes par genre."""
     ensure_parent_dir(path)

scripts/list_new_minifig_characters.py

@@ -0,0 +1,39 @@
+"""Liste les nouveaux personnages introduits chaque année et leurs sets associés."""
+
+from pathlib import Path
+
+from lib.rebrickable.minifig_character_sets import load_sets
+from lib.rebrickable.minifig_characters import (
+    aggregate_new_character_sets,
+    load_minifigs_by_set,
+    write_new_character_sets_csv,
+    write_new_character_sets_markdown,
+)
+
+
+MINIFIGS_BY_SET_PATH = Path("data/intermediate/minifigs_by_set.csv")
+SETS_ENRICHED_PATH = Path("data/intermediate/sets_enriched.csv")
+CSV_DESTINATION_PATH = Path("data/final/minifig_new_characters_by_year.csv")
+MARKDOWN_DESTINATION_PATH = Path("data/final/minifig_new_characters_by_year.md")
+EXCLUDED_CHARACTERS = ["Figurant"]
+START_YEAR = 2015
+END_YEAR = 2025
+
+
+def main() -> None:
+    """Construit le CSV et le Markdown listant les personnages introduits chaque année."""
+    minifigs = load_minifigs_by_set(MINIFIGS_BY_SET_PATH)
+    sets_lookup = load_sets(SETS_ENRICHED_PATH)
+    rows = aggregate_new_character_sets(
+        minifigs,
+        sets_lookup,
+        excluded_characters=EXCLUDED_CHARACTERS,
+        start_year=START_YEAR,
+        end_year=END_YEAR,
+    )
+    write_new_character_sets_csv(CSV_DESTINATION_PATH, rows)
+    write_new_character_sets_markdown(MARKDOWN_DESTINATION_PATH, rows)
+
+
+if __name__ == "__main__":
+    main()

tests/test_minifig_characters.py

@@ -5,16 +5,20 @@ from pathlib import Path
 from lib.rebrickable.minifig_characters import (
     aggregate_by_character,
     aggregate_by_gender,
+    aggregate_new_character_sets,
     aggregate_new_characters_by_year,
     aggregate_variations_and_totals,
     aggregate_character_spans,
     aggregate_presence_by_year,
     load_sets_enriched,
     write_character_counts,
+    write_new_character_sets_csv,
+    write_new_character_sets_markdown,
     write_new_characters_by_year,
     write_character_variations_totals,
     write_gender_counts,
 )
+from lib.rebrickable.minifig_character_sets import load_sets
 
 
 def test_aggregate_by_character_counts_unique_figs() -> None:
@@ -143,11 +147,11 @@ def test_aggregate_new_characters_by_year_limits_range(tmp_path: Path) -> None:
     """Compter les nouveaux personnages par année en respectant la plage."""
     sets_path = tmp_path / "sets_enriched.csv"
     sets_path.write_text(
-        "set_num,year\n"
+        "set_num,name,year,theme_id,num_parts,img_url,set_id,rebrickable_url,in_collection\n"
-        "123-1,2015\n"
+        "123-1,Set A,2015,0,0,,-,http://r/123-1,true\n"
-        "124-1,2016\n"
+        "124-1,Set B,2016,0,0,,-,http://r/124-1,true\n"
-        "125-1,2017\n"
+        "125-1,Set C,2017,0,0,,-,http://r/125-1,true\n"
-        "126-1,2014\n"
+        "126-1,Set D,2014,0,0,,-,http://r/126-1,true\n"
     )
     sets_years = load_sets_enriched(sets_path)
     minifigs_rows = [
@@ -172,6 +176,59 @@ def test_aggregate_new_characters_by_year_limits_range(tmp_path: Path) -> None:
     ]
 
 
+def test_aggregate_new_character_sets_returns_intro_sets(tmp_path: Path) -> None:
+    """Lister les personnages introduits avec les sets de l'année d'introduction."""
+    sets_path = tmp_path / "sets_enriched.csv"
+    sets_path.write_text(
+        "set_num,name,year,theme_id,num_parts,img_url,set_id,rebrickable_url,in_collection\n"
+        "123-1,Set A,2015,0,0,,123,http://r/123-1,true\n"
+        "124-1,Set B,2015,0,0,,124,http://r/124-1,true\n"
+        "125-1,Set C,2016,0,0,,125,http://r/125-1,true\n"
+    )
+    sets_lookup = load_sets(sets_path)
+    minifigs_rows = [
+        {"set_num": "123-1", "known_character": "Owen Grady", "fig_num": "fig-owen-1", "part_num": "head-a"},
+        {"set_num": "124-1", "known_character": "Owen Grady", "fig_num": "fig-owen-2", "part_num": "head-b"},
+        {"set_num": "125-1", "known_character": "Owen Grady", "fig_num": "fig-owen-3", "part_num": "head-c"},
+        {"set_num": "125-1", "known_character": "Ellie Sattler", "fig_num": "fig-ellie-1", "part_num": "head-d"},
+    ]
+
+    rows = aggregate_new_character_sets(
+        minifigs_rows,
+        sets_lookup,
+        excluded_characters=["Figurant"],
+        start_year=2015,
+        end_year=2016,
+    )
+
+    assert rows == [
+        {
+            "year": "2015",
+            "known_character": "Owen Grady",
+            "set_num": "123-1",
+            "set_id": "123",
+            "set_name": "Set A",
+            "rebrickable_url": "http://r/123-1",
+        },
+        {
+            "year": "2015",
+            "known_character": "Owen Grady",
+            "set_num": "124-1",
+            "set_id": "124",
+            "set_name": "Set B",
+            "rebrickable_url": "http://r/124-1",
+        },
+        {
+            "year": "2016",
+            "known_character": "Ellie Sattler",
+            "set_num": "125-1",
+            "set_id": "125",
+            "set_name": "Set C",
+            "rebrickable_url": "http://r/125-1",
+        },
+    ]
+
+
 def test_write_character_counts_outputs_csv(tmp_path: Path) -> None:
     """Écrit le CSV des comptes par personnage."""
     destination = tmp_path / "counts.csv"
@@ -224,6 +281,42 @@ def test_write_new_characters_by_year_outputs_csv(tmp_path: Path) -> None:
     assert destination.read_text() == "year,new_characters\n2015,3\n2016,1\n"
 
 
+def test_write_new_character_sets_markdown_outputs_md(tmp_path: Path) -> None:
+    """Écrit le Markdown listant les nouveaux personnages et leurs sets."""
+    destination = tmp_path / "new_characters.md"
+    rows = [
+        {
+            "year": "2015",
+            "known_character": "Owen Grady",
+            "set_num": "123-1",
+            "set_id": "123",
+            "set_name": "Set A",
+            "rebrickable_url": "http://r/123-1",
+        },
+        {
+            "year": "2016",
+            "known_character": "Ellie Sattler",
+            "set_num": "125-1",
+            "set_id": "125",
+            "set_name": "Set C",
+            "rebrickable_url": "http://r/125-1",
+        },
+    ]
+
+    write_new_character_sets_markdown(destination, rows)
+
+    assert destination.read_text() == (
+        "##### 2015\n\n"
+        "- Owen Grady\n"
+        "    - [123](http://r/123-1) - Set A\n"
+        "\n"
+        "##### 2016\n\n"
+        "- Ellie Sattler\n"
+        "    - [125](http://r/125-1) - Set C\n"
+        "\n"
+    )
+
+
 def test_aggregate_presence_by_year_excludes_figurants(tmp_path: Path) -> None:
     """Calcule le total annuel en excluant les figurants."""
     sets_path = tmp_path / "sets_enriched.csv"