jlhe97
diff --git a/‎dossier/report.py‎
Lines changed: 159 additions & 1 deletion b/‎dossier/report.py‎
Lines changed: 159 additions & 1 deletion
diff --git a/‎pipeline/runner.py‎
Lines changed: 22 additions & 13 deletions b/‎pipeline/runner.py‎
Lines changed: 22 additions & 13 deletions
@@ -135,6 +135,162 @@ def render_markdown(dossier: dict) -> str:
     return "\n".join(lines)
 
 
+_HTML_CSS = """
+body { font-family: Georgia, serif; max-width: 960px; margin: 2rem auto; padding: 0 1.5rem; color: #1a1a1a; }
+h1 { border-bottom: 2px solid #333; padding-bottom: .4rem; }
+h2 { margin-top: 2rem; color: #2c2c2c; }
+h3 { margin-top: 1.2rem; color: #444; }
+.meta { color: #666; font-style: italic; margin-bottom: 1.5rem; }
+.profiles { list-style: none; padding: 0; }
+.profiles li { margin: .3rem 0; }
+.warn { color: #c0392b; font-style: italic; }
+table { border-collapse: collapse; width: 100%; margin: .8rem 0; font-size: .92rem; }
+th { background: #2c3e50; color: #fff; padding: .45rem .7rem; text-align: left; }
+td { padding: .35rem .7rem; border-bottom: 1px solid #ddd; }
+tr:nth-child(even) td { background: #f7f7f7; }
+.line { font-family: monospace; font-size: .85rem; }
+.wp-hi  { background: #c8f7c5 !important; }
+.wp-mid { background: #fef9c3 !important; }
+.wp-lo  { background: #fcd6d6 !important; }
+.overview td:first-child { font-weight: bold; }
+.section-white { border-left: 4px solid #f0c040; padding-left: .8rem; }
+.section-black { border-left: 4px solid #444; padding-left: .8rem; }
+@media print { .player-section { page-break-after: always; } }
+"""
+
+
+def render_html(dossier: dict) -> str:
+    player = dossier["player"]
+    body = _html_player_section(
+        player, dossier["stats"], dossier["openings"],
+        dossier["profiles"], dossier["generated"]
+    )
+    return (
+        f"<!doctype html><html lang='en'><head>"
+        f"<meta charset='utf-8'><title>Dossier: {_esc(player)}</title>"
+        f"<style>{_HTML_CSS}</style></head><body>"
+        + body + "</body></html>"
+    )
+
+
+def render_html_combined(dossiers: list[dict]) -> str:
+    def _nav_item(d):
+        pid = _slug_id(d["player"])
+        return f"<li><a href='#{pid}'>{_esc(d['player'])}</a></li>"
+
+    nav_links = "".join(_nav_item(d) for d in dossiers)
+    nav = f"<nav><h2>Players</h2><ul>{nav_links}</ul></nav><hr>"
+
+    sections = "".join(
+        _html_player_section(
+            d["player"], d["stats"], d["openings"], d["profiles"], d["generated"],
+            anchor=_slug_id(d["player"])
+        )
+        for d in dossiers
+    )
+    return (
+        "<!doctype html><html lang='en'><head>"
+        "<meta charset='utf-8'><title>Tournament Dossiers</title>"
+        f"<style>{_HTML_CSS}</style></head><body>"
+        + nav + sections + "</body></html>"
+    )
+
+
+def _slug_id(name: str) -> str:
+    return re.sub(r"[^a-z0-9]+", "_", name.lower()).strip("_")
+
+
+def _esc(s: str) -> str:
+    return s.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
+
+
+def _html_player_section(player, stats, openings, profiles, generated, anchor=None) -> str:
+    aid = f" id='{anchor}'" if anchor else ""
+    ov  = stats["overall"]
+
+    def wp_class(pct):
+        if pct >= 55:  return "wp-hi"
+        if pct >= 40:  return "wp-mid"
+        return "wp-lo"
+
+    # --- profiles ---
+    prof_html = ""
+    if profiles:
+        items = []
+        for p in profiles:
+            site    = "Lichess" if "lichess" in p.get("url", "") else "chess.com"
+            ratings = ", ".join(f"{k.capitalize()}: {v}" for k, v in p.get("ratings", {}).items())
+            title   = f"{p['title']} " if p.get("title") else ""
+            warn    = " <span class='warn'>⚠ low-confidence match</span>" if p.get("confidence") == "low" else ""
+            rat_str = f" — {_esc(ratings)}" if ratings else ""
+            items.append(
+                f"<li><strong>{site}</strong>: "
+                f"<a href='{p['url']}'>{_esc(title)}{_esc(p['display_name'])}</a>"
+                f"{rat_str}{warn}</li>"
+            )
+        prof_html = f"<h2>Online Profiles</h2><ul class='profiles'>{''.join(items)}</ul>"
+
+    # --- overview table ---
+    aw, ab = stats["as_white"], stats["as_black"]
+    overview = (
+        "<h2>Overview</h2>"
+        "<table class='overview'>"
+        "<tr><th></th><th>White</th><th>Black</th><th>Overall</th></tr>"
+        f"<tr><td>Games</td><td>{aw['count']}</td><td>{ab['count']}</td><td>{stats['total']}</td></tr>"
+        f"<tr><td>Wins</td><td>{aw['wins']}</td><td>{ab['wins']}</td><td>{ov['wins']}</td></tr>"
+        f"<tr><td>Draws</td><td>{aw['draws']}</td><td>{ab['draws']}</td><td>{ov['draws']}</td></tr>"
+        f"<tr><td>Losses</td><td>{aw['losses']}</td><td>{ab['losses']}</td><td>{ov['losses']}</td></tr>"
+        f"<tr><td>Win %</td>"
+        f"<td class='{wp_class(aw['win_pct'])}'>{aw['win_pct']}%</td>"
+        f"<td class='{wp_class(ab['win_pct'])}'>{ab['win_pct']}%</td>"
+        f"<td class='{wp_class(ov['win_pct'])}'>{ov['win_pct']}%</td>"
+        "</tr></table>"
+        f"<p><strong>Average game length:</strong> {stats['avg_length']} half-moves</p>"
+    )
+
+    # --- as white ---
+    white_body = (
+        _html_opening_table(openings["as_white"], wp_class)
+        if openings["as_white"] else "<p><em>No games found as White.</em></p>"
+    )
+    as_white = f"<div class='section-white'><h2>As White</h2>{white_body}</div>"
+
+    # --- as black ---
+    black_parts = []
+    if stats["vs_e4"]:
+        black_parts.append(f"<h3>vs 1. e4</h3>{_html_opening_table(stats['vs_e4'], wp_class)}")
+    if stats["vs_d4"]:
+        black_parts.append(f"<h3>vs 1. d4</h3>{_html_opening_table(stats['vs_d4'], wp_class)}")
+    if openings["as_black"]:
+        black_parts.append(
+            f"<h3>All openings as Black</h3>{_html_opening_table(openings['as_black'], wp_class)}"
+        )
+    if not black_parts:
+        black_parts.append("<p><em>No games found as Black.</em></p>")
+    as_black = f"<div class='section-black'><h2>As Black</h2>{''.join(black_parts)}</div>"
+
+    return (
+        f"<section class='player-section'{aid}>"
+        f"<h1>Dossier: {_esc(player)}</h1>"
+        f"<p class='meta'>Generated {_esc(generated)} · {stats['total']} games analysed</p>"
+        + prof_html + overview + as_white + as_black
+        + "</section>"
+    )
+
+
+def _html_opening_table(rows: list[dict], wp_class) -> str:
+    header = "<tr><th>Opening</th><th>Games</th><th>W</th><th>D</th><th>L</th><th>Win%</th></tr>"
+    def _row(r):
+        cls = wp_class(r["win_pct"])
+        return (
+            f"<tr><td class='line'>{_esc(r['line'])}</td>"
+            f"<td>{r['count']}</td><td>{r['wins']}</td>"
+            f"<td>{r['draws']}</td><td>{r['losses']}</td>"
+            f"<td class='{cls}'>{r['win_pct']}%</td></tr>"
+        )
+    return f"<table>{header}{''.join(_row(r) for r in rows)}</table>"
+
+
 def render_json(dossier: dict) -> str:
     return json.dumps(dossier, indent=2, ensure_ascii=False)
 
@@ -200,7 +356,7 @@ def main() -> None:
                         help="Opening depth in half-moves (default: 6)")
     parser.add_argument("--top",   type=int, default=8,
                         help="Top N opening lines per colour (default: 8)")
-    parser.add_argument("--output", choices=["markdown", "json"], default="markdown")
+    parser.add_argument("--output", choices=["markdown", "html", "json"], default="html")
     args = parser.parse_args()
 
     pgn_strings: list[str] = []
@@ -231,6 +387,8 @@ def main() -> None:
 
     if args.output == "json":
         print(render_json(dossier))
+    elif args.output == "html":
+        print(render_html(dossier))
     else:
         print(render_markdown(dossier))
 
 
@@ -5,12 +5,12 @@
   python -m pipeline.runner Challenge34
   python -m pipeline.runner Challenge34 --site kingregistration --output-dir ./dossiers
   python -m pipeline.runner "https://chessaction.com/tournaments/advance_entry_list.php?tid=nKGioA=="
-  python -m pipeline.runner Challenge34 --max-games 30 --format json
+  python -m pipeline.runner Challenge34 --max-games 30 --format html
 
-Output (default):
+Output (default html):
   <output-dir>/
-    smith_john.md       ← one file per opponent
-    combined.md         ← all dossiers concatenated (print-friendly)
+    smith_john.html     ← one file per opponent
+    combined.html       ← all dossiers with nav (printable)
 """
 
 import re
@@ -19,7 +19,7 @@
 from pathlib import Path
 
 from scraper import scrape_entry_list
-from dossier.report import build_dossier, render_markdown, render_json
+from dossier.report import build_dossier, render_markdown, render_html, render_html_combined, render_json
 from pipeline.resolver import resolve_lichess, resolve_chesscom
 
 
@@ -72,7 +72,7 @@ def run_pipeline(
     chesscom_months: int = 3,
     depth: int = 6,
     top: int = 8,
-    fmt: str = "markdown",
+    fmt: str = "html",
 ) -> list[Path]:
     """
     Run the full pipeline for a tournament. Returns list of written file paths.
@@ -88,7 +88,7 @@ def run_pipeline(
     print(f"Found {len(players)} player(s).", file=sys.stderr)
 
     written: list[Path] = []
-    combined_parts: list[str] = []
+    dossiers: list[dict] = []
 
     for i, player in enumerate(players, 1):
         name = player.get("name", "").strip()
@@ -129,25 +129,34 @@ def run_pipeline(
 
         dossier = build_dossier(name, pgn_strings, profiles=profiles,
                                 depth=depth, top=top)
+        dossiers.append(dossier)
 
         if fmt == "json":
             content = render_json(dossier)
             ext = "json"
+        elif fmt == "html":
+            content = render_html(dossier)
+            ext = "html"
         else:
             content = render_markdown(dossier)
             ext = "md"
 
         path = out / f"{_slug(name)}.{ext}"
         path.write_text(content, encoding="utf-8")
         written.append(path)
-        combined_parts.append(content)
         print(f"  Saved → {path}", file=sys.stderr)
 
     # --- Combined output ---
-    if combined_parts and fmt == "markdown":
-        sep = "\n\n---\n\n"
+    if dossiers and fmt == "markdown":
         combined = out / "combined.md"
-        combined.write_text(sep.join(combined_parts), encoding="utf-8")
+        combined.write_text(
+            "\n\n---\n\n".join(render_markdown(d) for d in dossiers), encoding="utf-8"
+        )
+        written.append(combined)
+        print(f"\nCombined → {combined}", file=sys.stderr)
+    elif dossiers and fmt == "html":
+        combined = out / "combined.html"
+        combined.write_text(render_html_combined(dossiers), encoding="utf-8")
         written.append(combined)
         print(f"\nCombined → {combined}", file=sys.stderr)
 
@@ -172,8 +181,8 @@ def main() -> None:
                         help="Opening depth in half-moves (default: 6)")
     parser.add_argument("--top", type=int, default=8,
                         help="Top N opening lines per colour (default: 8)")
-    parser.add_argument("--format", dest="fmt", choices=["markdown", "json"],
-                        default="markdown")
+    parser.add_argument("--format", dest="fmt", choices=["markdown", "html", "json"],
+                        default="html")
     args = parser.parse_args()
 
     run_pipeline(