Spaces:
Running
Running
Claude commited on
refactor(report): regrouper renderers depuis extras/render/
Browse filesLes 6 renderers HTML qui vivaient dans ``picarones/extras/render/``
sont déplacés dans ``picarones/report/`` (où vivent déjà les ~16
autres renderers). Le rendu HTML est l'identité visible de Picarones —
pas un plugin tiers — et n'a aucune raison d'être éparpillé entre
deux dossiers.
Renderers déplacés :
- image_predictive_render
- lexical_modernization_render
- module_audit_render
- philological_render
- taxonomy_cooccurrence_render
- taxonomy_intra_doc_render
Le sous-package ``extras/render/`` est supprimé. Les fichiers
historiquement présents dans ``report/`` (qui étaient des shims
pointant vers ``extras/render/``) sont écrasés par les vraies
sources.
https://claude.ai/code/session_01Hsd7kL8yeCbXn1mA7GQK9L
- picarones/extras/render/__init__.py +0 -13
- picarones/extras/render/image_predictive_render.py +0 -221
- picarones/extras/render/lexical_modernization_render.py +0 -119
- picarones/extras/render/module_audit_render.py +0 -173
- picarones/extras/render/philological_render.py +0 -615
- picarones/extras/render/taxonomy_cooccurrence_render.py +0 -199
- picarones/extras/render/taxonomy_intra_doc_render.py +0 -182
- picarones/report/image_predictive_render.py +217 -22
- picarones/report/lexical_modernization_render.py +111 -18
- picarones/report/module_audit_render.py +169 -22
- picarones/report/philological_render.py +607 -18
- picarones/report/taxonomy_cooccurrence_render.py +191 -18
- picarones/report/taxonomy_intra_doc_render.py +174 -18
picarones/extras/render/__init__.py
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
"""Renderers atomiques pour les modules ``extras/``.
|
| 2 |
-
|
| 3 |
-
Importés conditionnellement par les vues thématiques du chantier 3
|
| 4 |
-
(``picarones.report.views.advanced_taxonomy``, etc.) qui restent
|
| 5 |
-
dans le Cercle 2. Si les modules ``extras/academic/`` ou
|
| 6 |
-
``extras/governance/`` sont absents, ces renderers ne sont pas
|
| 7 |
-
sollicités et la vue masque la sous-section.
|
| 8 |
-
|
| 9 |
-
Rétrocompat
|
| 10 |
-
-----------
|
| 11 |
-
Imports historiques ``from picarones.report.taxonomy_intra_doc_render
|
| 12 |
-
import ...`` continuent à fonctionner via des fichiers-shims.
|
| 13 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/image_predictive_render.py
DELETED
|
@@ -1,221 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML « Profil d'image du corpus » — Sprint 93 (A.II.7).
|
| 2 |
-
|
| 3 |
-
Suite directe ``picarones/core/image_predictive.py``. Pattern
|
| 4 |
-
identique aux autres rendus : server-side, pas de JS, anti-
|
| 5 |
-
injection systématique.
|
| 6 |
-
|
| 7 |
-
Vue
|
| 8 |
-
---
|
| 9 |
-
Deux blocs dans une section unique :
|
| 10 |
-
|
| 11 |
-
1. **Complexité paléographique** : moyenne, médiane, min, max,
|
| 12 |
-
écart-type sur l'ensemble du corpus.
|
| 13 |
-
2. **Homogénéité du corpus** : score combiné + détail par
|
| 14 |
-
feature (mean, stdev, contribution normalisée).
|
| 15 |
-
|
| 16 |
-
Adaptive : ``""`` si pas de données.
|
| 17 |
-
|
| 18 |
-
Note d'intégration
|
| 19 |
-
------------------
|
| 20 |
-
Module pur — l'utilisateur compose :
|
| 21 |
-
|
| 22 |
-
.. code-block:: python
|
| 23 |
-
|
| 24 |
-
from picarones.core.image_predictive import aggregate_corpus_predictive
|
| 25 |
-
from picarones.report.image_predictive_render import (
|
| 26 |
-
build_image_predictive_html,
|
| 27 |
-
)
|
| 28 |
-
|
| 29 |
-
qualities = [doc.image_quality.as_dict() for doc in benchmark.docs]
|
| 30 |
-
agg = aggregate_corpus_predictive(qualities)
|
| 31 |
-
html = build_image_predictive_html(agg, labels)
|
| 32 |
-
"""
|
| 33 |
-
|
| 34 |
-
from __future__ import annotations
|
| 35 |
-
|
| 36 |
-
from html import escape as _e
|
| 37 |
-
from typing import Optional
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
def _color_for_score(score: float) -> str:
|
| 41 |
-
"""Vert (faible) → orange → rouge (élevé)."""
|
| 42 |
-
f = max(0.0, min(1.0, score))
|
| 43 |
-
if f < 0.5:
|
| 44 |
-
t = f / 0.5
|
| 45 |
-
r = int(167 + (235 - 167) * t)
|
| 46 |
-
g = int(240 + (180 - 240) * t)
|
| 47 |
-
b = int(167 + (60 - 167) * t)
|
| 48 |
-
else:
|
| 49 |
-
t = (f - 0.5) / 0.5
|
| 50 |
-
r = int(235 + (220 - 235) * t)
|
| 51 |
-
g = int(180 + (50 - 180) * t)
|
| 52 |
-
b = int(60 + (50 - 60) * t)
|
| 53 |
-
return f"#{r:02x}{g:02x}{b:02x}"
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
_FEATURE_LABEL_KEYS = {
|
| 57 |
-
"noise_level": "imgpred_feat_noise",
|
| 58 |
-
"sharpness_score": "imgpred_feat_sharpness",
|
| 59 |
-
"contrast_score": "imgpred_feat_contrast",
|
| 60 |
-
"rotation_degrees": "imgpred_feat_rotation",
|
| 61 |
-
}
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
def _render_complexity_block(
|
| 65 |
-
aggregated: dict, labels: dict[str, str],
|
| 66 |
-
) -> str:
|
| 67 |
-
h_complex = labels.get(
|
| 68 |
-
"imgpred_complexity", "Complexité paléographique",
|
| 69 |
-
)
|
| 70 |
-
h_mean = labels.get("imgpred_mean", "Moyenne")
|
| 71 |
-
h_median = labels.get("imgpred_median", "Médiane")
|
| 72 |
-
h_min = labels.get("imgpred_min", "Min")
|
| 73 |
-
h_max = labels.get("imgpred_max", "Max")
|
| 74 |
-
h_stdev = labels.get("imgpred_stdev", "Écart-type")
|
| 75 |
-
h_docs = labels.get("imgpred_docs", "Docs")
|
| 76 |
-
mean = float(aggregated.get("complexity_mean") or 0.0)
|
| 77 |
-
median = float(aggregated.get("complexity_median") or 0.0)
|
| 78 |
-
mn = float(aggregated.get("complexity_min") or 0.0)
|
| 79 |
-
mx = float(aggregated.get("complexity_max") or 0.0)
|
| 80 |
-
sd = float(aggregated.get("complexity_stdev") or 0.0)
|
| 81 |
-
n_docs = int(aggregated.get("n_docs") or 0)
|
| 82 |
-
color_mean = _color_for_score(mean)
|
| 83 |
-
return (
|
| 84 |
-
f'<div style="font-weight:600;margin:.4rem 0 .3rem 0">'
|
| 85 |
-
f'{_e(h_complex)}</div>'
|
| 86 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 87 |
-
'font-size:.9rem;margin-bottom:.8rem">'
|
| 88 |
-
f'<thead><tr>'
|
| 89 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 90 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_mean)}</th>'
|
| 91 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 92 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_median)}</th>'
|
| 93 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 94 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_min)}</th>'
|
| 95 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 96 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_max)}</th>'
|
| 97 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 98 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_stdev)}</th>'
|
| 99 |
-
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 100 |
-
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_docs)}</th>'
|
| 101 |
-
f'</tr></thead>'
|
| 102 |
-
f'<tbody><tr>'
|
| 103 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 104 |
-
f'background:{color_mean};font-family:monospace;font-weight:600">'
|
| 105 |
-
f'{mean:.3f}</td>'
|
| 106 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 107 |
-
f'font-family:monospace">{median:.3f}</td>'
|
| 108 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 109 |
-
f'font-family:monospace">{mn:.3f}</td>'
|
| 110 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 111 |
-
f'font-family:monospace">{mx:.3f}</td>'
|
| 112 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 113 |
-
f'font-family:monospace">{sd:.3f}</td>'
|
| 114 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 115 |
-
f'font-family:monospace">{n_docs}</td>'
|
| 116 |
-
f'</tr></tbody></table>'
|
| 117 |
-
)
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
def _render_homogeneity_block(
|
| 121 |
-
homogeneity: dict, labels: dict[str, str],
|
| 122 |
-
) -> str:
|
| 123 |
-
h_homo = labels.get(
|
| 124 |
-
"imgpred_homogeneity", "Homogénéité du corpus",
|
| 125 |
-
)
|
| 126 |
-
h_feat = labels.get("imgpred_feature", "Feature")
|
| 127 |
-
h_mean = labels.get("imgpred_feat_mean", "Moyenne")
|
| 128 |
-
h_stdev = labels.get("imgpred_feat_stdev", "Écart-type")
|
| 129 |
-
h_norm = labels.get(
|
| 130 |
-
"imgpred_feat_norm", "Contribution normalisée",
|
| 131 |
-
)
|
| 132 |
-
score = float(homogeneity.get("score") or 0.0)
|
| 133 |
-
color = _color_for_score(score)
|
| 134 |
-
parts = [
|
| 135 |
-
f'<div style="font-weight:600;margin:.4rem 0 .3rem 0">'
|
| 136 |
-
f'{_e(h_homo)} : '
|
| 137 |
-
f'<span style="background:{color};padding:.1rem .4rem;'
|
| 138 |
-
f'border-radius:.3rem;font-family:monospace">{score:.3f}</span>'
|
| 139 |
-
f'</div>',
|
| 140 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 141 |
-
'font-size:.9rem">',
|
| 142 |
-
'<thead><tr>',
|
| 143 |
-
]
|
| 144 |
-
for col in (h_feat, h_mean, h_stdev, h_norm):
|
| 145 |
-
parts.append(
|
| 146 |
-
f'<th style="padding:.4rem .6rem;text-align:left;'
|
| 147 |
-
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 148 |
-
f'{_e(col)}</th>'
|
| 149 |
-
)
|
| 150 |
-
parts.append("</tr></thead><tbody>")
|
| 151 |
-
per_feat = homogeneity.get("per_feature") or {}
|
| 152 |
-
for key, label_key in _FEATURE_LABEL_KEYS.items():
|
| 153 |
-
if key not in per_feat:
|
| 154 |
-
continue
|
| 155 |
-
slot = per_feat[key]
|
| 156 |
-
feat_label = labels.get(label_key, key)
|
| 157 |
-
feat_mean = float(slot.get("mean") or 0.0)
|
| 158 |
-
feat_stdev = float(slot.get("stdev") or 0.0)
|
| 159 |
-
feat_norm = float(slot.get("normalised") or 0.0)
|
| 160 |
-
norm_color = _color_for_score(feat_norm)
|
| 161 |
-
parts.append(
|
| 162 |
-
f'<tr>'
|
| 163 |
-
f'<td style="padding:.4rem .6rem">{_e(feat_label)}</td>'
|
| 164 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 165 |
-
f'font-family:monospace">{feat_mean:.3f}</td>'
|
| 166 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 167 |
-
f'font-family:monospace">{feat_stdev:.3f}</td>'
|
| 168 |
-
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 169 |
-
f'background:{norm_color};font-family:monospace">'
|
| 170 |
-
f'{feat_norm:.3f}</td>'
|
| 171 |
-
f'</tr>'
|
| 172 |
-
)
|
| 173 |
-
parts.append("</tbody></table>")
|
| 174 |
-
return "".join(parts)
|
| 175 |
-
|
| 176 |
-
|
| 177 |
-
def build_image_predictive_html(
|
| 178 |
-
aggregated: Optional[dict],
|
| 179 |
-
labels: Optional[dict[str, str]] = None,
|
| 180 |
-
) -> str:
|
| 181 |
-
"""Construit la vue HTML « Profil d'image du corpus ».
|
| 182 |
-
|
| 183 |
-
Parameters
|
| 184 |
-
----------
|
| 185 |
-
aggregated:
|
| 186 |
-
Sortie de ``aggregate_corpus_predictive``. Si ``None``
|
| 187 |
-
ou ``n_docs == 0``, retourne ``""``.
|
| 188 |
-
labels:
|
| 189 |
-
Dict i18n. Clés sous le préfixe ``imgpred_*``.
|
| 190 |
-
"""
|
| 191 |
-
if not aggregated:
|
| 192 |
-
return ""
|
| 193 |
-
if not aggregated.get("n_docs"):
|
| 194 |
-
return ""
|
| 195 |
-
labels = labels or {}
|
| 196 |
-
title = labels.get(
|
| 197 |
-
"imgpred_title", "Profil d'image du corpus",
|
| 198 |
-
)
|
| 199 |
-
note = labels.get(
|
| 200 |
-
"imgpred_note",
|
| 201 |
-
"Score de complexité paléographique combinant bruit, "
|
| 202 |
-
"flou, faible contraste et rotation. Le score "
|
| 203 |
-
"d'homogénéité signale si la moyenne globale est fiable "
|
| 204 |
-
"(corpus uniforme) ou trompeuse (corpus hétérogène — "
|
| 205 |
-
"voir alors la vue stratifiée).",
|
| 206 |
-
)
|
| 207 |
-
parts = [
|
| 208 |
-
'<section class="imgpred-section" style="margin:1rem 0">',
|
| 209 |
-
f'<h3 style="margin:0 0 .3rem 0">{_e(title)}</h3>',
|
| 210 |
-
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.6rem">'
|
| 211 |
-
f'{_e(note)}</div>',
|
| 212 |
-
]
|
| 213 |
-
parts.append(_render_complexity_block(aggregated, labels))
|
| 214 |
-
homo = aggregated.get("homogeneity")
|
| 215 |
-
if isinstance(homo, dict):
|
| 216 |
-
parts.append(_render_homogeneity_block(homo, labels))
|
| 217 |
-
parts.append("</section>")
|
| 218 |
-
return "".join(parts)
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
__all__ = ["build_image_predictive_html"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/lexical_modernization_render.py
DELETED
|
@@ -1,119 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML de la vue « Modernisation lexicale » — Sprint 80.
|
| 2 |
-
|
| 3 |
-
A.I.7 du plan d'évolution 2026.
|
| 4 |
-
|
| 5 |
-
Suite directe ``picarones/core/lexical_modernization.py``.
|
| 6 |
-
Pattern identique aux autres rendus (Sprints 41/43/62/67/72/74/75/76/77) :
|
| 7 |
-
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
-
|
| 9 |
-
Vue
|
| 10 |
-
---
|
| 11 |
-
Tableau trié par taux de modernisation décroissant : forme
|
| 12 |
-
historique GT → forme(s) modernisée(s), occurrences GT, %.
|
| 13 |
-
Couleur de cellule pour le %.
|
| 14 |
-
"""
|
| 15 |
-
|
| 16 |
-
from __future__ import annotations
|
| 17 |
-
|
| 18 |
-
from html import escape as _e
|
| 19 |
-
from typing import Optional
|
| 20 |
-
|
| 21 |
-
from picarones.core.lexical_modernization import top_modernized_tokens
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
def _color_for_rate(rate: float) -> str:
|
| 25 |
-
"""Gradient blanc → orange profond pour rate ∈ [0, 1]."""
|
| 26 |
-
f = max(0.0, min(1.0, rate))
|
| 27 |
-
r = int(255 + (194 - 255) * f)
|
| 28 |
-
g = int(255 + (65 - 255) * f)
|
| 29 |
-
b = int(255 + (12 - 255) * f)
|
| 30 |
-
return f"#{r:02x}{g:02x}{b:02x}"
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
def _format_variants(variants: dict, max_show: int = 3) -> str:
|
| 34 |
-
"""Liste compacte des variants modernisés."""
|
| 35 |
-
items = sorted(variants.items(), key=lambda kv: -kv[1])
|
| 36 |
-
shown = items[:max_show]
|
| 37 |
-
rest = len(items) - max_show
|
| 38 |
-
parts = [
|
| 39 |
-
f"{_e(form)} ({count})"
|
| 40 |
-
for form, count in shown
|
| 41 |
-
]
|
| 42 |
-
if rest > 0:
|
| 43 |
-
parts.append(f"+{rest}")
|
| 44 |
-
return ", ".join(parts)
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
def build_lexical_modernization_html(
|
| 48 |
-
data: Optional[dict],
|
| 49 |
-
labels: Optional[dict[str, str]] = None,
|
| 50 |
-
*,
|
| 51 |
-
top_n: int = 20,
|
| 52 |
-
min_total: int = 1,
|
| 53 |
-
) -> str:
|
| 54 |
-
"""Construit la table HTML de modernisation lexicale.
|
| 55 |
-
|
| 56 |
-
Retourne ``""`` si ``data is None`` ou si aucun token modernisé.
|
| 57 |
-
"""
|
| 58 |
-
if not data:
|
| 59 |
-
return ""
|
| 60 |
-
rows = top_modernized_tokens(data, n=top_n, min_total=min_total)
|
| 61 |
-
if not rows:
|
| 62 |
-
return ""
|
| 63 |
-
labels = labels or {}
|
| 64 |
-
title = labels.get(
|
| 65 |
-
"lexmod_title", "Modernisation lexicale (top tokens)",
|
| 66 |
-
)
|
| 67 |
-
note = labels.get(
|
| 68 |
-
"lexmod_note",
|
| 69 |
-
"Tokens GT que le moteur réécrit le plus souvent. "
|
| 70 |
-
"Lecture : « maistre → maître modernisé dans 85 % des cas » "
|
| 71 |
-
"indique de quoi corriger dans le prompt pour préserver "
|
| 72 |
-
"l'orthographe historique.",
|
| 73 |
-
)
|
| 74 |
-
gt_label = labels.get("lexmod_gt_label", "Forme historique GT")
|
| 75 |
-
hyp_label = labels.get("lexmod_hyp_label", "Variantes OCR")
|
| 76 |
-
n_label = labels.get("lexmod_n_label", "n GT")
|
| 77 |
-
rate_label = labels.get("lexmod_rate_label", "% modernisé")
|
| 78 |
-
|
| 79 |
-
parts = [
|
| 80 |
-
'<div class="lexmod" style="margin:1rem 0">',
|
| 81 |
-
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 82 |
-
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 83 |
-
f'{_e(note)}</div>',
|
| 84 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 85 |
-
'font-size:.85rem">',
|
| 86 |
-
'<thead><tr>',
|
| 87 |
-
]
|
| 88 |
-
for col in (gt_label, hyp_label, n_label, rate_label):
|
| 89 |
-
parts.append(
|
| 90 |
-
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 91 |
-
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 92 |
-
f'{_e(col)}</th>'
|
| 93 |
-
)
|
| 94 |
-
parts.append("</tr></thead><tbody>")
|
| 95 |
-
for gt_token, slot in rows:
|
| 96 |
-
rate = slot.get("rate_modernized", 0.0)
|
| 97 |
-
n_total = slot.get("n_total", 0)
|
| 98 |
-
variants_str = _format_variants(slot.get("variants") or {})
|
| 99 |
-
rate_color = _color_for_rate(rate)
|
| 100 |
-
parts.append(
|
| 101 |
-
f'<tr>'
|
| 102 |
-
f'<td style="padding:.3rem .5rem;font-family:monospace">'
|
| 103 |
-
f'{_e(gt_token)}</td>'
|
| 104 |
-
f'<td style="padding:.3rem .5rem;font-size:.85rem">'
|
| 105 |
-
f'{variants_str}</td>'
|
| 106 |
-
f'<td style="padding:.3rem .5rem;text-align:right;'
|
| 107 |
-
f'font-family:monospace">{n_total}</td>'
|
| 108 |
-
f'<td style="padding:.3rem .5rem;text-align:right;'
|
| 109 |
-
f'background:{rate_color};font-family:monospace">'
|
| 110 |
-
f'{rate * 100:.0f}%</td>'
|
| 111 |
-
f'</tr>'
|
| 112 |
-
)
|
| 113 |
-
parts.append("</tbody></table></div>")
|
| 114 |
-
return "".join(parts)
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
__all__ = [
|
| 118 |
-
"build_lexical_modernization_html",
|
| 119 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/module_audit_render.py
DELETED
|
@@ -1,173 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML « Modules audités » — Sprint 97 (B.6).
|
| 2 |
-
|
| 3 |
-
Suite directe ``picarones/core/module_policy.py``. Pattern
|
| 4 |
-
identique aux autres rendus : server-side, pas de JS, anti-
|
| 5 |
-
injection systématique.
|
| 6 |
-
|
| 7 |
-
Vue
|
| 8 |
-
---
|
| 9 |
-
Tableau récapitulatif des modules utilisés dans une pipeline
|
| 10 |
-
composée, chacun avec :
|
| 11 |
-
|
| 12 |
-
- Statut d'audit (✓ vert si tous les checks passent, ✗ rouge
|
| 13 |
-
sinon, avec compte des échecs) ;
|
| 14 |
-
- Métadonnées : version, auteur, licence ;
|
| 15 |
-
- Citation académique si fournie ;
|
| 16 |
-
- Lien vers la homepage si fourni.
|
| 17 |
-
|
| 18 |
-
Adaptive : ``""`` si la liste est vide.
|
| 19 |
-
|
| 20 |
-
Note d'intégration
|
| 21 |
-
------------------
|
| 22 |
-
Module pur — l'utilisateur compose la liste depuis sa
|
| 23 |
-
``PipelineSpec`` augmentée des ``ModuleManifest`` :
|
| 24 |
-
|
| 25 |
-
.. code-block:: python
|
| 26 |
-
|
| 27 |
-
from picarones.core.module_policy import audit_module
|
| 28 |
-
from picarones.report.module_audit_render import build_module_audit_html
|
| 29 |
-
|
| 30 |
-
audits = []
|
| 31 |
-
for step in pipeline.steps:
|
| 32 |
-
manifest = step.module.manifest # convention applicative
|
| 33 |
-
result = audit_module(step.module, manifest)
|
| 34 |
-
audits.append({
|
| 35 |
-
"manifest": manifest.as_dict(),
|
| 36 |
-
"audit": result.as_dict(),
|
| 37 |
-
})
|
| 38 |
-
html = build_module_audit_html(audits, labels)
|
| 39 |
-
"""
|
| 40 |
-
|
| 41 |
-
from __future__ import annotations
|
| 42 |
-
|
| 43 |
-
from html import escape as _e
|
| 44 |
-
from typing import Optional
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
def _passed_badge(passed: bool, n_failed: int, label_pass: str,
|
| 48 |
-
label_fail: str) -> str:
|
| 49 |
-
if passed:
|
| 50 |
-
return (
|
| 51 |
-
f'<span style="color:#16a34a;font-weight:700">'
|
| 52 |
-
f'✓ {_e(label_pass)}</span>'
|
| 53 |
-
)
|
| 54 |
-
return (
|
| 55 |
-
f'<span style="color:#dc2626;font-weight:700">'
|
| 56 |
-
f'✗ {_e(label_fail)} ({n_failed})</span>'
|
| 57 |
-
)
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
def build_module_audit_html(
|
| 61 |
-
audits: Optional[list],
|
| 62 |
-
labels: Optional[dict[str, str]] = None,
|
| 63 |
-
) -> str:
|
| 64 |
-
"""Construit la vue HTML « Modules audités ».
|
| 65 |
-
|
| 66 |
-
Parameters
|
| 67 |
-
----------
|
| 68 |
-
audits:
|
| 69 |
-
Liste de dicts ``{"manifest": ManifestDict, "audit":
|
| 70 |
-
AuditResultDict}``. Si vide ou ``None``, retourne ``""``.
|
| 71 |
-
labels:
|
| 72 |
-
Dict i18n. Clés sous le préfixe ``audit_*``.
|
| 73 |
-
"""
|
| 74 |
-
if not audits:
|
| 75 |
-
return ""
|
| 76 |
-
rows = [
|
| 77 |
-
a for a in audits
|
| 78 |
-
if isinstance(a, dict)
|
| 79 |
-
and isinstance(a.get("manifest"), dict)
|
| 80 |
-
and isinstance(a.get("audit"), dict)
|
| 81 |
-
]
|
| 82 |
-
if not rows:
|
| 83 |
-
return ""
|
| 84 |
-
labels = labels or {}
|
| 85 |
-
title = labels.get("audit_title", "Modules audités")
|
| 86 |
-
note = labels.get(
|
| 87 |
-
"audit_note",
|
| 88 |
-
"Récapitulatif des modules utilisés dans la pipeline "
|
| 89 |
-
"composée. Un module qui ne passe pas l'audit n'est "
|
| 90 |
-
"pas exécutable. Métadonnées issues du manifest fourni "
|
| 91 |
-
"par le contributeur (auteur, licence, citation).",
|
| 92 |
-
)
|
| 93 |
-
label_pass = labels.get("audit_pass", "audit OK")
|
| 94 |
-
label_fail = labels.get("audit_fail", "checks échoués")
|
| 95 |
-
h_module = labels.get("audit_module", "Module")
|
| 96 |
-
h_status = labels.get("audit_status", "Audit")
|
| 97 |
-
h_version = labels.get("audit_version", "Version")
|
| 98 |
-
h_author = labels.get("audit_author", "Auteur")
|
| 99 |
-
h_license = labels.get("audit_license", "Licence")
|
| 100 |
-
h_io = labels.get("audit_io", "Entrée → sortie")
|
| 101 |
-
h_citation = labels.get("audit_citation", "Citation")
|
| 102 |
-
h_homepage = labels.get("audit_homepage", "Page projet")
|
| 103 |
-
|
| 104 |
-
parts = [
|
| 105 |
-
'<section class="audit-section" style="margin:1rem 0">',
|
| 106 |
-
f'<h3 style="margin:0 0 .3rem 0">{_e(title)}</h3>',
|
| 107 |
-
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 108 |
-
f'{_e(note)}</div>',
|
| 109 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 110 |
-
'font-size:.9rem">',
|
| 111 |
-
'<thead><tr>',
|
| 112 |
-
]
|
| 113 |
-
for col in (h_module, h_status, h_version, h_author,
|
| 114 |
-
h_license, h_io, h_citation, h_homepage):
|
| 115 |
-
parts.append(
|
| 116 |
-
f'<th style="padding:.4rem .6rem;text-align:left;'
|
| 117 |
-
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 118 |
-
f'{_e(col)}</th>'
|
| 119 |
-
)
|
| 120 |
-
parts.append("</tr></thead><tbody>")
|
| 121 |
-
|
| 122 |
-
for entry in rows:
|
| 123 |
-
manifest = entry["manifest"]
|
| 124 |
-
audit = entry["audit"]
|
| 125 |
-
name = str(manifest.get("name") or "?")
|
| 126 |
-
version = str(manifest.get("version") or "—")
|
| 127 |
-
author = str(manifest.get("author") or "—")
|
| 128 |
-
license_ = str(manifest.get("license") or "—")
|
| 129 |
-
in_types = ", ".join(manifest.get("input_types") or []) or "—"
|
| 130 |
-
out_types = ", ".join(manifest.get("output_types") or []) or "—"
|
| 131 |
-
citation = manifest.get("citation") or ""
|
| 132 |
-
homepage = manifest.get("homepage") or ""
|
| 133 |
-
passed = bool(audit.get("passed"))
|
| 134 |
-
n_failed = int(audit.get("n_failed") or 0)
|
| 135 |
-
status_cell = _passed_badge(
|
| 136 |
-
passed, n_failed, label_pass, label_fail,
|
| 137 |
-
)
|
| 138 |
-
# Citation : tronqué si trop long
|
| 139 |
-
citation_str = str(citation)[:120]
|
| 140 |
-
if len(str(citation)) > 120:
|
| 141 |
-
citation_str += "…"
|
| 142 |
-
citation_cell = (
|
| 143 |
-
_e(citation_str) if citation_str.strip() else "—"
|
| 144 |
-
)
|
| 145 |
-
# Homepage : on n'auto-link **pas** (anti-injection +
|
| 146 |
-
# honnêteté : l'URL peut pointer ailleurs). On affiche
|
| 147 |
-
# le texte échappé tel quel.
|
| 148 |
-
homepage_cell = (
|
| 149 |
-
_e(str(homepage))[:80] + ("…" if len(str(homepage)) > 80 else "")
|
| 150 |
-
) if str(homepage).strip() else "—"
|
| 151 |
-
parts.append(
|
| 152 |
-
f'<tr>'
|
| 153 |
-
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 154 |
-
f'{_e(name)}</td>'
|
| 155 |
-
f'<td style="padding:.4rem .6rem">{status_cell}</td>'
|
| 156 |
-
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 157 |
-
f'{_e(version)}</td>'
|
| 158 |
-
f'<td style="padding:.4rem .6rem">{_e(author)}</td>'
|
| 159 |
-
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 160 |
-
f'{_e(license_)}</td>'
|
| 161 |
-
f'<td style="padding:.4rem .6rem;font-family:monospace;'
|
| 162 |
-
f'font-size:.8rem">{_e(in_types)} → {_e(out_types)}</td>'
|
| 163 |
-
f'<td style="padding:.4rem .6rem;font-size:.8rem;'
|
| 164 |
-
f'opacity:.85">{citation_cell}</td>'
|
| 165 |
-
f'<td style="padding:.4rem .6rem;font-family:monospace;'
|
| 166 |
-
f'font-size:.8rem">{homepage_cell}</td>'
|
| 167 |
-
f'</tr>'
|
| 168 |
-
)
|
| 169 |
-
parts.append("</tbody></table></section>")
|
| 170 |
-
return "".join(parts)
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
__all__ = ["build_module_audit_html"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/philological_render.py
DELETED
|
@@ -1,615 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML server-side du profil philologique (Sprint 62).
|
| 2 |
-
|
| 3 |
-
Suite directe Sprint 61 (câblage backend) — produit les blocs HTML
|
| 4 |
-
qui exposent les six modules philologiques (Sprints 55-60) dans le
|
| 5 |
-
rapport :
|
| 6 |
-
|
| 7 |
-
- ``unicode_blocks`` (Sprint 55) — précision par bloc Unicode
|
| 8 |
-
- ``abbreviations`` (Sprint 56) — score strict + expansion par
|
| 9 |
-
abréviation médiévale Capelli
|
| 10 |
-
- ``mufi`` (Sprint 57) — couverture MUFI globale + par
|
| 11 |
-
caractère
|
| 12 |
-
- ``early_modern`` (Sprint 58) — préservation des marqueurs
|
| 13 |
-
typographiques imprimé ancien
|
| 14 |
-
- ``modern_archives`` (Sprint 59) — strict + expansion par
|
| 15 |
-
catégorie d'archive moderne
|
| 16 |
-
- ``roman_numerals`` (Sprint 60) — breakdown 5 statuts de
|
| 17 |
-
restitution
|
| 18 |
-
|
| 19 |
-
Principe identique aux Sprints 41 (NER) et 43 (calibration) :
|
| 20 |
-
|
| 21 |
-
- Rendu **server-side**, pas de JavaScript, déterministe.
|
| 22 |
-
- Section adaptive : si aucun moteur n'a de signal pour un module
|
| 23 |
-
donné, la sous-section est silencieusement omise.
|
| 24 |
-
- Si **aucun module** n'a de signal sur l'ensemble des moteurs,
|
| 25 |
-
``build_philological_profile_html`` retourne une chaîne vide et
|
| 26 |
-
le bloc complet n'apparaît pas dans la vue analyses.
|
| 27 |
-
- **Aucune classification automatique** : on affiche les chiffres
|
| 28 |
-
bruts par catégorie/bloc/statut, le chercheur juge lui-même la
|
| 29 |
-
convention adoptée.
|
| 30 |
-
- Anti-injection : tous les noms de moteurs, catégories, statuts,
|
| 31 |
-
caractères passent par ``html.escape`` avant insertion.
|
| 32 |
-
"""
|
| 33 |
-
|
| 34 |
-
from __future__ import annotations
|
| 35 |
-
|
| 36 |
-
from html import escape as _e
|
| 37 |
-
from typing import Optional
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 41 |
-
# Helpers de coloration
|
| 42 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
def _color_for_score(score: float) -> str:
|
| 46 |
-
"""Gradient rouge → jaune → vert proportionnel à ``score`` ∈ [0, 1].
|
| 47 |
-
|
| 48 |
-
Identique à ``ner_render._color_for_f1``. Les scores
|
| 49 |
-
philologiques (preservation, coverage, accuracy) suivent la même
|
| 50 |
-
sémantique « plus c'est haut, mieux c'est » donc le gradient
|
| 51 |
-
est valide.
|
| 52 |
-
"""
|
| 53 |
-
f = max(0.0, min(1.0, score))
|
| 54 |
-
if f <= 0.5:
|
| 55 |
-
ratio = f / 0.5
|
| 56 |
-
r = int(220 + (240 - 220) * ratio)
|
| 57 |
-
g = int(100 + (220 - 100) * ratio)
|
| 58 |
-
b = int(100 + (130 - 100) * ratio)
|
| 59 |
-
else:
|
| 60 |
-
ratio = (f - 0.5) / 0.5
|
| 61 |
-
r = int(240 + (130 - 240) * ratio)
|
| 62 |
-
g = int(220 + (200 - 220) * ratio)
|
| 63 |
-
b = int(130 + (130 - 130) * ratio)
|
| 64 |
-
return f"#{r:02x}{g:02x}{b:02x}"
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
def _engines_with_module(
|
| 68 |
-
engines_summary: list[dict], module: str,
|
| 69 |
-
) -> list[dict]:
|
| 70 |
-
"""Filtre les moteurs ayant des données pour le module donné."""
|
| 71 |
-
out: list[dict] = []
|
| 72 |
-
for eng in engines_summary:
|
| 73 |
-
agg = eng.get("aggregated_philological") or {}
|
| 74 |
-
if module in agg and agg[module]:
|
| 75 |
-
out.append(eng)
|
| 76 |
-
return out
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
def _score_cell(score: Optional[float], extra: str = "") -> str:
|
| 80 |
-
"""Rend une cellule colorée. ``None`` → cellule grise « — »."""
|
| 81 |
-
if score is None:
|
| 82 |
-
return (
|
| 83 |
-
'<td style="padding:.3rem .5rem;text-align:center;'
|
| 84 |
-
'background:#f0f0f0;color:#999">—</td>'
|
| 85 |
-
)
|
| 86 |
-
color = _color_for_score(score)
|
| 87 |
-
text = f"{score * 100:.1f}%"
|
| 88 |
-
if extra:
|
| 89 |
-
text += f" <span style=\"opacity:.6;font-size:.85em\">({_e(extra)})</span>"
|
| 90 |
-
return (
|
| 91 |
-
f'<td style="padding:.3rem .5rem;text-align:center;'
|
| 92 |
-
f'background:{color}">{text}</td>'
|
| 93 |
-
)
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
def _table_header(
|
| 97 |
-
columns: list[str], engine_label: str,
|
| 98 |
-
) -> str:
|
| 99 |
-
"""Construit l'entête d'un tableau moteur × colonnes."""
|
| 100 |
-
parts = [
|
| 101 |
-
'<thead><tr>',
|
| 102 |
-
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 103 |
-
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 104 |
-
f'{_e(engine_label)}</th>',
|
| 105 |
-
]
|
| 106 |
-
for col in columns:
|
| 107 |
-
parts.append(
|
| 108 |
-
f'<th style="padding:.3rem .5rem;text-align:center;'
|
| 109 |
-
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 110 |
-
f'{_e(col)}</th>'
|
| 111 |
-
)
|
| 112 |
-
parts.append('</tr></thead>')
|
| 113 |
-
return "".join(parts)
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
def _engine_label_cell(name: str) -> str:
|
| 117 |
-
return (
|
| 118 |
-
f'<td style="padding:.3rem .5rem;font-weight:500;'
|
| 119 |
-
f'border-bottom:1px solid var(--border-light)">{_e(name)}</td>'
|
| 120 |
-
)
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
def _section_open(title: str, note: str = "") -> str:
|
| 124 |
-
parts = [
|
| 125 |
-
'<div class="philological-section" '
|
| 126 |
-
'style="margin:1rem 0;padding:.75rem;'
|
| 127 |
-
'background:var(--bg-secondary);border-radius:6px">',
|
| 128 |
-
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 129 |
-
]
|
| 130 |
-
if note:
|
| 131 |
-
parts.append(
|
| 132 |
-
f'<div style="font-size:.8rem;opacity:.75;margin-bottom:.5rem">'
|
| 133 |
-
f'{_e(note)}</div>'
|
| 134 |
-
)
|
| 135 |
-
return "".join(parts)
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
def _section_close() -> str:
|
| 139 |
-
return "</div>"
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
def _table_open() -> str:
|
| 143 |
-
return (
|
| 144 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 145 |
-
'font-size:.85rem">'
|
| 146 |
-
)
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
def _table_close() -> str:
|
| 150 |
-
return "</table>"
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 154 |
-
# Sprint 55 — Précision par bloc Unicode
|
| 155 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
def build_unicode_blocks_section(
|
| 159 |
-
engines_summary: list[dict],
|
| 160 |
-
labels: Optional[dict[str, str]] = None,
|
| 161 |
-
) -> str:
|
| 162 |
-
relevant = _engines_with_module(engines_summary, "unicode_blocks")
|
| 163 |
-
if not relevant:
|
| 164 |
-
return ""
|
| 165 |
-
labels = labels or {}
|
| 166 |
-
title = labels.get(
|
| 167 |
-
"philo_unicode_blocks_title", "Précision par bloc Unicode",
|
| 168 |
-
)
|
| 169 |
-
note = labels.get(
|
| 170 |
-
"philo_unicode_blocks_note",
|
| 171 |
-
"Pourcentage de caractères correctement restitués par bloc "
|
| 172 |
-
"Unicode rencontré dans la GT (hors Basic Latin).",
|
| 173 |
-
)
|
| 174 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 175 |
-
global_label = labels.get("philo_global_label", "Global")
|
| 176 |
-
|
| 177 |
-
# Collecte tous les blocs présents (hors Basic Latin déjà filtré
|
| 178 |
-
# par adaptive masking, mais on défilte ici si Basic Latin
|
| 179 |
-
# apparaît malgré tout chez certains moteurs).
|
| 180 |
-
all_blocks: set[str] = set()
|
| 181 |
-
for eng in relevant:
|
| 182 |
-
per_block = eng["aggregated_philological"]["unicode_blocks"].get(
|
| 183 |
-
"per_block", {},
|
| 184 |
-
)
|
| 185 |
-
for block in per_block:
|
| 186 |
-
if block != "Basic Latin":
|
| 187 |
-
all_blocks.add(block)
|
| 188 |
-
blocks = sorted(all_blocks)
|
| 189 |
-
if not blocks:
|
| 190 |
-
return ""
|
| 191 |
-
|
| 192 |
-
parts = [_section_open(title, note), _table_open()]
|
| 193 |
-
parts.append(_table_header([global_label] + blocks, engine_label))
|
| 194 |
-
parts.append("<tbody>")
|
| 195 |
-
for eng in relevant:
|
| 196 |
-
agg = eng["aggregated_philological"]["unicode_blocks"]
|
| 197 |
-
global_acc = agg.get("global_accuracy", 0.0)
|
| 198 |
-
n_chars = agg.get("n_chars_total", 0)
|
| 199 |
-
parts.append("<tr>")
|
| 200 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 201 |
-
parts.append(_score_cell(global_acc, extra=f"n={n_chars}"))
|
| 202 |
-
per_block = agg.get("per_block", {})
|
| 203 |
-
for block in blocks:
|
| 204 |
-
stats = per_block.get(block)
|
| 205 |
-
if stats and stats.get("total", 0) > 0:
|
| 206 |
-
parts.append(_score_cell(
|
| 207 |
-
stats["accuracy"], extra=f"n={stats['total']}",
|
| 208 |
-
))
|
| 209 |
-
else:
|
| 210 |
-
parts.append(_score_cell(None))
|
| 211 |
-
parts.append("</tr>")
|
| 212 |
-
parts.append("</tbody>")
|
| 213 |
-
parts.append(_table_close())
|
| 214 |
-
parts.append(_section_close())
|
| 215 |
-
return "".join(parts)
|
| 216 |
-
|
| 217 |
-
|
| 218 |
-
# (sections suivantes définies plus loin)
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 222 |
-
# Sprint 56 — Abréviations Capelli médiévales
|
| 223 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
def build_abbreviations_section(
|
| 227 |
-
engines_summary: list[dict],
|
| 228 |
-
labels: Optional[dict[str, str]] = None,
|
| 229 |
-
) -> str:
|
| 230 |
-
relevant = _engines_with_module(engines_summary, "abbreviations")
|
| 231 |
-
if not relevant:
|
| 232 |
-
return ""
|
| 233 |
-
labels = labels or {}
|
| 234 |
-
title = labels.get(
|
| 235 |
-
"philo_abbreviations_title",
|
| 236 |
-
"Abréviations médiévales (Capelli)",
|
| 237 |
-
)
|
| 238 |
-
note = labels.get(
|
| 239 |
-
"philo_abbreviations_note",
|
| 240 |
-
"Strict = forme abrégée (ꝑ, ꝓ, ⁊…) préservée telle quelle ; "
|
| 241 |
-
"Expansion = abrégée OU forme développée (per, pro, et…) "
|
| 242 |
-
"présente. Le ratio strict/expansion par moteur indique la "
|
| 243 |
-
"convention adoptée (diplomatique / modernisante).",
|
| 244 |
-
)
|
| 245 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 246 |
-
strict_label = labels.get("philo_strict_label", "Strict")
|
| 247 |
-
expansion_label = labels.get("philo_expansion_label", "Expansion")
|
| 248 |
-
n_label = labels.get("philo_n_total_label", "n total")
|
| 249 |
-
|
| 250 |
-
parts = [_section_open(title, note), _table_open()]
|
| 251 |
-
parts.append(_table_header(
|
| 252 |
-
[strict_label, expansion_label, n_label], engine_label,
|
| 253 |
-
))
|
| 254 |
-
parts.append("<tbody>")
|
| 255 |
-
for eng in relevant:
|
| 256 |
-
agg = eng["aggregated_philological"]["abbreviations"]
|
| 257 |
-
parts.append("<tr>")
|
| 258 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 259 |
-
parts.append(_score_cell(agg.get("global_strict_score", 0.0)))
|
| 260 |
-
parts.append(_score_cell(agg.get("global_expansion_score", 0.0)))
|
| 261 |
-
parts.append(
|
| 262 |
-
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 263 |
-
f'{agg.get("n_abbreviations_in_reference", 0)}</td>'
|
| 264 |
-
)
|
| 265 |
-
parts.append("</tr>")
|
| 266 |
-
parts.append("</tbody>")
|
| 267 |
-
parts.append(_table_close())
|
| 268 |
-
parts.append(_section_close())
|
| 269 |
-
return "".join(parts)
|
| 270 |
-
|
| 271 |
-
|
| 272 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 273 |
-
# Sprint 57 — Couverture MUFI
|
| 274 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 275 |
-
|
| 276 |
-
|
| 277 |
-
def build_mufi_section(
|
| 278 |
-
engines_summary: list[dict],
|
| 279 |
-
labels: Optional[dict[str, str]] = None,
|
| 280 |
-
) -> str:
|
| 281 |
-
relevant = _engines_with_module(engines_summary, "mufi")
|
| 282 |
-
if not relevant:
|
| 283 |
-
return ""
|
| 284 |
-
labels = labels or {}
|
| 285 |
-
title = labels.get(
|
| 286 |
-
"philo_mufi_title",
|
| 287 |
-
"Couverture MUFI (Medieval Unicode Font Initiative)",
|
| 288 |
-
)
|
| 289 |
-
note = labels.get(
|
| 290 |
-
"philo_mufi_note",
|
| 291 |
-
"Taux de caractères MUFI de la GT (þ, ð, ƿ, ſ, æ, lettres "
|
| 292 |
-
"PUA…) correctement restitués dans l'OCR. Critère éditorial "
|
| 293 |
-
"central pour les médiévistes.",
|
| 294 |
-
)
|
| 295 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 296 |
-
coverage_label = labels.get("philo_mufi_coverage_label", "Couverture")
|
| 297 |
-
n_label = labels.get("philo_n_total_label", "n total")
|
| 298 |
-
|
| 299 |
-
parts = [_section_open(title, note), _table_open()]
|
| 300 |
-
parts.append(_table_header(
|
| 301 |
-
[coverage_label, n_label], engine_label,
|
| 302 |
-
))
|
| 303 |
-
parts.append("<tbody>")
|
| 304 |
-
for eng in relevant:
|
| 305 |
-
agg = eng["aggregated_philological"]["mufi"]
|
| 306 |
-
parts.append("<tr>")
|
| 307 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 308 |
-
parts.append(_score_cell(agg.get("coverage", 0.0)))
|
| 309 |
-
parts.append(
|
| 310 |
-
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 311 |
-
f'{agg.get("n_mufi_chars_reference", 0)}</td>'
|
| 312 |
-
)
|
| 313 |
-
parts.append("</tr>")
|
| 314 |
-
parts.append("</tbody>")
|
| 315 |
-
parts.append(_table_close())
|
| 316 |
-
parts.append(_section_close())
|
| 317 |
-
return "".join(parts)
|
| 318 |
-
|
| 319 |
-
|
| 320 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 321 |
-
# Sprint 58 — Marqueurs typographiques imprimé ancien (heatmap)
|
| 322 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 323 |
-
|
| 324 |
-
|
| 325 |
-
def build_early_modern_section(
|
| 326 |
-
engines_summary: list[dict],
|
| 327 |
-
labels: Optional[dict[str, str]] = None,
|
| 328 |
-
) -> str:
|
| 329 |
-
relevant = _engines_with_module(engines_summary, "early_modern")
|
| 330 |
-
if not relevant:
|
| 331 |
-
return ""
|
| 332 |
-
labels = labels or {}
|
| 333 |
-
title = labels.get(
|
| 334 |
-
"philo_early_modern_title",
|
| 335 |
-
"Marqueurs typographiques imprimé ancien (XVIᵉ-XVIIIᵉ)",
|
| 336 |
-
)
|
| 337 |
-
note = labels.get(
|
| 338 |
-
"philo_early_modern_note",
|
| 339 |
-
"Préservation des ligatures (fi fl ff), s long (ſ), i sans "
|
| 340 |
-
"point (ı), esperluette (&) et tildes nasaux (ã õ ñ). "
|
| 341 |
-
"Une ligne par moteur, une colonne par catégorie.",
|
| 342 |
-
)
|
| 343 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 344 |
-
global_label = labels.get("philo_global_label", "Global")
|
| 345 |
-
|
| 346 |
-
all_cats: set[str] = set()
|
| 347 |
-
for eng in relevant:
|
| 348 |
-
all_cats.update(
|
| 349 |
-
eng["aggregated_philological"]["early_modern"]
|
| 350 |
-
.get("per_category", {}).keys(),
|
| 351 |
-
)
|
| 352 |
-
cats = sorted(all_cats)
|
| 353 |
-
if not cats:
|
| 354 |
-
return ""
|
| 355 |
-
|
| 356 |
-
parts = [_section_open(title, note), _table_open()]
|
| 357 |
-
parts.append(_table_header([global_label] + cats, engine_label))
|
| 358 |
-
parts.append("<tbody>")
|
| 359 |
-
for eng in relevant:
|
| 360 |
-
agg = eng["aggregated_philological"]["early_modern"]
|
| 361 |
-
n_total = agg.get("n_markers_reference", 0)
|
| 362 |
-
parts.append("<tr>")
|
| 363 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 364 |
-
parts.append(_score_cell(
|
| 365 |
-
agg.get("global_preservation", 0.0), extra=f"n={n_total}",
|
| 366 |
-
))
|
| 367 |
-
per_cat = agg.get("per_category", {})
|
| 368 |
-
for cat in cats:
|
| 369 |
-
stats = per_cat.get(cat)
|
| 370 |
-
if stats and stats.get("total", 0) > 0:
|
| 371 |
-
parts.append(_score_cell(
|
| 372 |
-
stats["preservation"], extra=f"n={stats['total']}",
|
| 373 |
-
))
|
| 374 |
-
else:
|
| 375 |
-
parts.append(_score_cell(None))
|
| 376 |
-
parts.append("</tr>")
|
| 377 |
-
parts.append("</tbody>")
|
| 378 |
-
parts.append(_table_close())
|
| 379 |
-
parts.append(_section_close())
|
| 380 |
-
return "".join(parts)
|
| 381 |
-
|
| 382 |
-
|
| 383 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 384 |
-
# Sprint 59 — Archives modernes : strict + expansion par catégorie
|
| 385 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 386 |
-
|
| 387 |
-
|
| 388 |
-
def build_modern_archives_section(
|
| 389 |
-
engines_summary: list[dict],
|
| 390 |
-
labels: Optional[dict[str, str]] = None,
|
| 391 |
-
) -> str:
|
| 392 |
-
relevant = _engines_with_module(engines_summary, "modern_archives")
|
| 393 |
-
if not relevant:
|
| 394 |
-
return ""
|
| 395 |
-
labels = labels or {}
|
| 396 |
-
title = labels.get(
|
| 397 |
-
"philo_modern_archives_title",
|
| 398 |
-
"Abréviations des archives modernes (XIXᵉ-XXᵉ)",
|
| 399 |
-
)
|
| 400 |
-
note = labels.get(
|
| 401 |
-
"philo_modern_archives_note",
|
| 402 |
-
"Strict = abrégé préservé (Mme, S.A.R., bd, vol., …) ; "
|
| 403 |
-
"Expansion = abrégé OU forme développée. Affiché par "
|
| 404 |
-
"catégorie : civilité, ordinaux, monnaie, administratif, "
|
| 405 |
-
"état civil, ponctuation typo, latin, biblio, adresse.",
|
| 406 |
-
)
|
| 407 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 408 |
-
global_label = labels.get("philo_global_label", "Global")
|
| 409 |
-
strict_label = labels.get("philo_strict_label", "Strict")
|
| 410 |
-
expansion_label = labels.get("philo_expansion_label", "Expansion")
|
| 411 |
-
|
| 412 |
-
all_cats: set[str] = set()
|
| 413 |
-
for eng in relevant:
|
| 414 |
-
all_cats.update(
|
| 415 |
-
eng["aggregated_philological"]["modern_archives"]
|
| 416 |
-
.get("per_category", {}).keys(),
|
| 417 |
-
)
|
| 418 |
-
cats = sorted(all_cats)
|
| 419 |
-
|
| 420 |
-
parts = [_section_open(title, note)]
|
| 421 |
-
parts.append(
|
| 422 |
-
'<table style="border-collapse:collapse;width:100%;'
|
| 423 |
-
'font-size:.85rem">'
|
| 424 |
-
)
|
| 425 |
-
parts.append("<thead><tr>")
|
| 426 |
-
parts.append(
|
| 427 |
-
f'<th rowspan="2" style="padding:.3rem .5rem;text-align:left;'
|
| 428 |
-
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 429 |
-
f'{_e(engine_label)}</th>'
|
| 430 |
-
)
|
| 431 |
-
parts.append(
|
| 432 |
-
f'<th colspan="2" style="padding:.3rem .5rem;text-align:center;'
|
| 433 |
-
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 434 |
-
f'{_e(global_label)}</th>'
|
| 435 |
-
)
|
| 436 |
-
for cat in cats:
|
| 437 |
-
parts.append(
|
| 438 |
-
f'<th colspan="2" style="padding:.3rem .5rem;text-align:center;'
|
| 439 |
-
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 440 |
-
f'{_e(cat)}</th>'
|
| 441 |
-
)
|
| 442 |
-
parts.append("</tr><tr>")
|
| 443 |
-
for _ in range(1 + len(cats)):
|
| 444 |
-
parts.append(
|
| 445 |
-
f'<th style="padding:.2rem .4rem;text-align:center;'
|
| 446 |
-
f'font-size:.75rem;font-weight:500;opacity:.7">'
|
| 447 |
-
f'{_e(strict_label)}</th>'
|
| 448 |
-
)
|
| 449 |
-
parts.append(
|
| 450 |
-
f'<th style="padding:.2rem .4rem;text-align:center;'
|
| 451 |
-
f'font-size:.75rem;font-weight:500;opacity:.7">'
|
| 452 |
-
f'{_e(expansion_label)}</th>'
|
| 453 |
-
)
|
| 454 |
-
parts.append("</tr></thead>")
|
| 455 |
-
parts.append("<tbody>")
|
| 456 |
-
for eng in relevant:
|
| 457 |
-
agg = eng["aggregated_philological"]["modern_archives"]
|
| 458 |
-
parts.append("<tr>")
|
| 459 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 460 |
-
parts.append(_score_cell(agg.get("global_strict_score", 0.0)))
|
| 461 |
-
parts.append(_score_cell(agg.get("global_expansion_score", 0.0)))
|
| 462 |
-
per_cat = agg.get("per_category", {})
|
| 463 |
-
for cat in cats:
|
| 464 |
-
stats = per_cat.get(cat)
|
| 465 |
-
if stats and stats.get("n_total", 0) > 0:
|
| 466 |
-
parts.append(_score_cell(
|
| 467 |
-
stats["strict_score"],
|
| 468 |
-
extra=f"n={stats['n_total']}",
|
| 469 |
-
))
|
| 470 |
-
parts.append(_score_cell(stats["expansion_score"]))
|
| 471 |
-
else:
|
| 472 |
-
parts.append(_score_cell(None))
|
| 473 |
-
parts.append(_score_cell(None))
|
| 474 |
-
parts.append("</tr>")
|
| 475 |
-
parts.append("</tbody>")
|
| 476 |
-
parts.append(_table_close())
|
| 477 |
-
parts.append(_section_close())
|
| 478 |
-
return "".join(parts)
|
| 479 |
-
|
| 480 |
-
|
| 481 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 482 |
-
# Sprint 60 — Numéraux romains : breakdown 5 statuts
|
| 483 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 484 |
-
|
| 485 |
-
|
| 486 |
-
def build_roman_numerals_section(
|
| 487 |
-
engines_summary: list[dict],
|
| 488 |
-
labels: Optional[dict[str, str]] = None,
|
| 489 |
-
) -> str:
|
| 490 |
-
relevant = _engines_with_module(engines_summary, "roman_numerals")
|
| 491 |
-
if not relevant:
|
| 492 |
-
return ""
|
| 493 |
-
labels = labels or {}
|
| 494 |
-
title = labels.get(
|
| 495 |
-
"philo_roman_numerals_title",
|
| 496 |
-
"Numéraux romains : restitution par statut",
|
| 497 |
-
)
|
| 498 |
-
note = labels.get(
|
| 499 |
-
"philo_roman_numerals_note",
|
| 500 |
-
"Pour chaque numéral romain de la GT, statut de restitution : "
|
| 501 |
-
"strict (forme exacte), case_changed (casse modifiée), "
|
| 502 |
-
"j_dropped (j médiéval normalisé), converted_to_arabic, lost. "
|
| 503 |
-
"Le breakdown indique la convention : majoritaire strict → "
|
| 504 |
-
"diplomatique ; majoritaire arabic → modernisation profonde.",
|
| 505 |
-
)
|
| 506 |
-
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 507 |
-
n_label = labels.get("philo_n_total_label", "n total")
|
| 508 |
-
|
| 509 |
-
statuses = (
|
| 510 |
-
"strict_preserved", "case_changed", "j_dropped",
|
| 511 |
-
"converted_to_arabic", "lost",
|
| 512 |
-
)
|
| 513 |
-
status_labels = {
|
| 514 |
-
s: labels.get(f"philo_roman_status_{s}", s) for s in statuses
|
| 515 |
-
}
|
| 516 |
-
|
| 517 |
-
parts = [_section_open(title, note), _table_open()]
|
| 518 |
-
parts.append(_table_header(
|
| 519 |
-
[n_label] + [status_labels[s] for s in statuses],
|
| 520 |
-
engine_label,
|
| 521 |
-
))
|
| 522 |
-
parts.append("<tbody>")
|
| 523 |
-
for eng in relevant:
|
| 524 |
-
agg = eng["aggregated_philological"]["roman_numerals"]
|
| 525 |
-
n_total = agg.get("n_numerals_reference", 0)
|
| 526 |
-
per_status = agg.get("per_status", {})
|
| 527 |
-
parts.append("<tr>")
|
| 528 |
-
parts.append(_engine_label_cell(eng["name"]))
|
| 529 |
-
parts.append(
|
| 530 |
-
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 531 |
-
f'{n_total}</td>'
|
| 532 |
-
)
|
| 533 |
-
for status in statuses:
|
| 534 |
-
count = per_status.get(status, 0)
|
| 535 |
-
if n_total > 0:
|
| 536 |
-
ratio = count / n_total
|
| 537 |
-
# Pour « lost » on inverse la couleur (un haut taux
|
| 538 |
-
# de perte est mauvais). Pour les autres on garde
|
| 539 |
-
# la sémantique « plus c'est haut, plus l'OCR a
|
| 540 |
-
# adopté ce statut ».
|
| 541 |
-
color = (
|
| 542 |
-
_color_for_score(1.0 - ratio) if status == "lost"
|
| 543 |
-
else _color_for_score(ratio)
|
| 544 |
-
)
|
| 545 |
-
parts.append(
|
| 546 |
-
f'<td style="padding:.3rem .5rem;text-align:center;'
|
| 547 |
-
f'background:{color}">{count} '
|
| 548 |
-
f'<span style="opacity:.6;font-size:.85em">'
|
| 549 |
-
f'({ratio * 100:.0f}%)</span></td>'
|
| 550 |
-
)
|
| 551 |
-
else:
|
| 552 |
-
parts.append(_score_cell(None))
|
| 553 |
-
parts.append("</tr>")
|
| 554 |
-
parts.append("</tbody>")
|
| 555 |
-
parts.append(_table_close())
|
| 556 |
-
parts.append(_section_close())
|
| 557 |
-
return "".join(parts)
|
| 558 |
-
|
| 559 |
-
|
| 560 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 561 |
-
# Agrégateur principal
|
| 562 |
-
# ──────────────────────────────────────────────────────────────────────────
|
| 563 |
-
|
| 564 |
-
|
| 565 |
-
def build_philological_profile_html(
|
| 566 |
-
engines_summary: list[dict],
|
| 567 |
-
labels: Optional[dict[str, str]] = None,
|
| 568 |
-
) -> str:
|
| 569 |
-
"""Assemble les six sections en un bloc unique.
|
| 570 |
-
|
| 571 |
-
Retourne ``""`` si aucune section n'a de contenu (c.-à-d.
|
| 572 |
-
aucun moteur n'a de signal philologique sur le corpus).
|
| 573 |
-
"""
|
| 574 |
-
sections = [
|
| 575 |
-
build_unicode_blocks_section(engines_summary, labels),
|
| 576 |
-
build_abbreviations_section(engines_summary, labels),
|
| 577 |
-
build_mufi_section(engines_summary, labels),
|
| 578 |
-
build_early_modern_section(engines_summary, labels),
|
| 579 |
-
build_modern_archives_section(engines_summary, labels),
|
| 580 |
-
build_roman_numerals_section(engines_summary, labels),
|
| 581 |
-
]
|
| 582 |
-
non_empty = [s for s in sections if s]
|
| 583 |
-
if not non_empty:
|
| 584 |
-
return ""
|
| 585 |
-
labels = labels or {}
|
| 586 |
-
main_title = labels.get(
|
| 587 |
-
"philo_profile_title", "Profil philologique",
|
| 588 |
-
)
|
| 589 |
-
main_note = labels.get(
|
| 590 |
-
"philo_profile_note",
|
| 591 |
-
"Données brutes par catégorie de marqueur philologique. "
|
| 592 |
-
"L'outil ne classifie pas la convention adoptée par chaque "
|
| 593 |
-
"moteur — c'est au chercheur de lire les chiffres et de "
|
| 594 |
-
"conclure selon ses critères éditoriaux.",
|
| 595 |
-
)
|
| 596 |
-
parts = [
|
| 597 |
-
'<div class="philological-profile">',
|
| 598 |
-
f'<h3 style="margin-top:0">{_e(main_title)}</h3>',
|
| 599 |
-
f'<p style="font-size:.85rem;opacity:.8;margin-bottom:.5rem">'
|
| 600 |
-
f'{_e(main_note)}</p>',
|
| 601 |
-
]
|
| 602 |
-
parts.extend(non_empty)
|
| 603 |
-
parts.append("</div>")
|
| 604 |
-
return "".join(parts)
|
| 605 |
-
|
| 606 |
-
|
| 607 |
-
__all__ = [
|
| 608 |
-
"build_philological_profile_html",
|
| 609 |
-
"build_unicode_blocks_section",
|
| 610 |
-
"build_abbreviations_section",
|
| 611 |
-
"build_mufi_section",
|
| 612 |
-
"build_early_modern_section",
|
| 613 |
-
"build_modern_archives_section",
|
| 614 |
-
"build_roman_numerals_section",
|
| 615 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/taxonomy_cooccurrence_render.py
DELETED
|
@@ -1,199 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML de la heatmap de co-occurrence taxonomique — Sprint 75.
|
| 2 |
-
|
| 3 |
-
A.I.4 chantier 1 du plan d'évolution 2026.
|
| 4 |
-
|
| 5 |
-
Suite directe ``picarones/core/taxonomy_cooccurrence.py``. Pattern
|
| 6 |
-
identique aux autres rendus (Sprints 41/43/62/67/72/74) :
|
| 7 |
-
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
-
|
| 9 |
-
Sortie typique
|
| 10 |
-
--------------
|
| 11 |
-
- ``build_taxonomy_cooccurrence_html(data, labels)`` produit un
|
| 12 |
-
bloc complet : titre + note d'usage + heatmap SVG + table des
|
| 13 |
-
paires les plus co-occurrentes.
|
| 14 |
-
- ``""`` retourné si ``data is None`` ou si la matrice est vide
|
| 15 |
-
(rapport adaptatif).
|
| 16 |
-
"""
|
| 17 |
-
|
| 18 |
-
from __future__ import annotations
|
| 19 |
-
|
| 20 |
-
from html import escape as _e
|
| 21 |
-
from typing import Optional
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
def _color_for_jaccard(j: float) -> str:
|
| 25 |
-
"""Gradient blanc → bleu profond pour Jaccard ∈ [0, 1].
|
| 26 |
-
|
| 27 |
-
Interpolation entre #ffffff (j=0) et #1e3a8a (j=1).
|
| 28 |
-
"""
|
| 29 |
-
f = max(0.0, min(1.0, j))
|
| 30 |
-
r = int(255 + (30 - 255) * f)
|
| 31 |
-
g = int(255 + (58 - 255) * f)
|
| 32 |
-
b = int(255 + (138 - 255) * f)
|
| 33 |
-
return f"#{r:02x}{g:02x}{b:02x}"
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
def _text_color_for_bg(j: float) -> str:
|
| 37 |
-
"""Texte blanc si fond foncé, noir sinon (lisibilité)."""
|
| 38 |
-
return "#fff" if j > 0.55 else "#222"
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
def _build_heatmap_svg(
|
| 42 |
-
classes: list[str],
|
| 43 |
-
matrix: dict[str, dict[str, float]],
|
| 44 |
-
*,
|
| 45 |
-
cell_size: int = 36,
|
| 46 |
-
label_left: int = 130,
|
| 47 |
-
label_top: int = 80,
|
| 48 |
-
) -> str:
|
| 49 |
-
"""Construit la heatmap SVG.
|
| 50 |
-
|
| 51 |
-
Cellule = carré coloré ``_color_for_jaccard``, valeur Jaccard
|
| 52 |
-
affichée en chiffres si > 0,05. Étiquettes des classes en
|
| 53 |
-
colonne (haut) et en ligne (gauche).
|
| 54 |
-
"""
|
| 55 |
-
n = len(classes)
|
| 56 |
-
if n == 0:
|
| 57 |
-
return ""
|
| 58 |
-
width = label_left + n * cell_size + 10
|
| 59 |
-
height = label_top + n * cell_size + 10
|
| 60 |
-
|
| 61 |
-
parts = [
|
| 62 |
-
f'<svg xmlns="http://www.w3.org/2000/svg" '
|
| 63 |
-
f'width="{width}" height="{height}" '
|
| 64 |
-
f'viewBox="0 0 {width} {height}" '
|
| 65 |
-
f'role="img" aria-label="Heatmap Jaccard co-occurrence taxonomique">',
|
| 66 |
-
]
|
| 67 |
-
# Étiquettes de colonnes (rotées -45°)
|
| 68 |
-
for j, cls in enumerate(classes):
|
| 69 |
-
cx = label_left + j * cell_size + cell_size // 2
|
| 70 |
-
cy = label_top - 6
|
| 71 |
-
parts.append(
|
| 72 |
-
f'<text x="{cx}" y="{cy}" '
|
| 73 |
-
f'transform="rotate(-45 {cx} {cy})" '
|
| 74 |
-
f'font-size="11" fill="#333" text-anchor="start">'
|
| 75 |
-
f'{_e(cls)}</text>'
|
| 76 |
-
)
|
| 77 |
-
# Étiquettes de lignes
|
| 78 |
-
for i, cls in enumerate(classes):
|
| 79 |
-
rx = label_left - 6
|
| 80 |
-
ry = label_top + i * cell_size + cell_size // 2 + 4
|
| 81 |
-
parts.append(
|
| 82 |
-
f'<text x="{rx}" y="{ry}" '
|
| 83 |
-
f'font-size="11" fill="#333" text-anchor="end">'
|
| 84 |
-
f'{_e(cls)}</text>'
|
| 85 |
-
)
|
| 86 |
-
# Cellules
|
| 87 |
-
for i, ca in enumerate(classes):
|
| 88 |
-
for j, cb in enumerate(classes):
|
| 89 |
-
value = matrix.get(ca, {}).get(cb, 0.0)
|
| 90 |
-
x = label_left + j * cell_size
|
| 91 |
-
y = label_top + i * cell_size
|
| 92 |
-
color = _color_for_jaccard(value)
|
| 93 |
-
text_color = _text_color_for_bg(value)
|
| 94 |
-
parts.append(
|
| 95 |
-
f'<rect x="{x}" y="{y}" '
|
| 96 |
-
f'width="{cell_size}" height="{cell_size}" '
|
| 97 |
-
f'fill="{color}" stroke="#ddd" stroke-width="0.5"/>'
|
| 98 |
-
)
|
| 99 |
-
if value > 0.05:
|
| 100 |
-
parts.append(
|
| 101 |
-
f'<text x="{x + cell_size // 2}" '
|
| 102 |
-
f'y="{y + cell_size // 2 + 4}" '
|
| 103 |
-
f'font-size="10" fill="{text_color}" '
|
| 104 |
-
f'text-anchor="middle">'
|
| 105 |
-
f'{value:.2f}</text>'
|
| 106 |
-
)
|
| 107 |
-
parts.append("</svg>")
|
| 108 |
-
return "".join(parts)
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
def _build_top_pairs_table(
|
| 112 |
-
top_pairs: list,
|
| 113 |
-
labels: dict,
|
| 114 |
-
) -> str:
|
| 115 |
-
"""Construit la table HTML des paires les plus co-occurrentes."""
|
| 116 |
-
if not top_pairs:
|
| 117 |
-
return ""
|
| 118 |
-
pair_label = labels.get("taxocooc_pair_label", "Paire")
|
| 119 |
-
jaccard_label = labels.get("taxocooc_jaccard_label", "Jaccard")
|
| 120 |
-
|
| 121 |
-
parts = [
|
| 122 |
-
'<table style="border-collapse:collapse;font-size:.85rem;'
|
| 123 |
-
'margin-top:.5rem">',
|
| 124 |
-
'<thead><tr>',
|
| 125 |
-
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 126 |
-
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 127 |
-
f'{_e(pair_label)}</th>',
|
| 128 |
-
f'<th style="padding:.3rem .5rem;text-align:right;'
|
| 129 |
-
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 130 |
-
f'{_e(jaccard_label)}</th>',
|
| 131 |
-
'</tr></thead><tbody>',
|
| 132 |
-
]
|
| 133 |
-
for ca, cb, j in top_pairs:
|
| 134 |
-
parts.append(
|
| 135 |
-
f'<tr>'
|
| 136 |
-
f'<td style="padding:.2rem .5rem">'
|
| 137 |
-
f'<code>{_e(ca)}</code> ↔ <code>{_e(cb)}</code></td>'
|
| 138 |
-
f'<td style="padding:.2rem .5rem;text-align:right;'
|
| 139 |
-
f'font-family:monospace;background:{_color_for_jaccard(j)};'
|
| 140 |
-
f'color:{_text_color_for_bg(j)}">{j:.2f}</td>'
|
| 141 |
-
f'</tr>'
|
| 142 |
-
)
|
| 143 |
-
parts.append("</tbody></table>")
|
| 144 |
-
return "".join(parts)
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
def build_taxonomy_cooccurrence_html(
|
| 148 |
-
data: Optional[dict],
|
| 149 |
-
labels: Optional[dict[str, str]] = None,
|
| 150 |
-
) -> str:
|
| 151 |
-
"""Construit le bloc HTML complet de co-occurrence taxonomique.
|
| 152 |
-
|
| 153 |
-
Retourne ``""`` si ``data is None`` ou matrice vide.
|
| 154 |
-
"""
|
| 155 |
-
if not data:
|
| 156 |
-
return ""
|
| 157 |
-
classes = data.get("classes") or []
|
| 158 |
-
matrix = data.get("cooccurrence_matrix") or {}
|
| 159 |
-
if not classes or not matrix:
|
| 160 |
-
return ""
|
| 161 |
-
labels = labels or {}
|
| 162 |
-
title = labels.get(
|
| 163 |
-
"taxocooc_title",
|
| 164 |
-
"Co-occurrence des classes d'erreur",
|
| 165 |
-
)
|
| 166 |
-
note = labels.get(
|
| 167 |
-
"taxocooc_note",
|
| 168 |
-
"Indice de Jaccard au niveau document : 1,00 = ces deux classes "
|
| 169 |
-
"apparaissent toujours ensemble ; 0,00 = jamais. Lecture par paires "
|
| 170 |
-
"co-occurrentes ci-dessous.",
|
| 171 |
-
)
|
| 172 |
-
n_docs = data.get("n_documents", 0)
|
| 173 |
-
n_docs_label_template = labels.get(
|
| 174 |
-
"taxocooc_n_docs", "Calculé sur {n_docs} documents.",
|
| 175 |
-
)
|
| 176 |
-
n_docs_phrase = n_docs_label_template.format(n_docs=n_docs)
|
| 177 |
-
|
| 178 |
-
svg = _build_heatmap_svg(classes, matrix)
|
| 179 |
-
top_table = _build_top_pairs_table(
|
| 180 |
-
data.get("top_pairs") or [], labels,
|
| 181 |
-
)
|
| 182 |
-
|
| 183 |
-
parts = [
|
| 184 |
-
'<div class="taxocooc" style="margin:1rem 0">',
|
| 185 |
-
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 186 |
-
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 187 |
-
f'{_e(note)}</div>',
|
| 188 |
-
f'<div style="font-size:.8rem;opacity:.7;margin-bottom:.5rem">'
|
| 189 |
-
f'{_e(n_docs_phrase)}</div>',
|
| 190 |
-
svg,
|
| 191 |
-
top_table,
|
| 192 |
-
"</div>",
|
| 193 |
-
]
|
| 194 |
-
return "".join(parts)
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
__all__ = [
|
| 198 |
-
"build_taxonomy_cooccurrence_html",
|
| 199 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/extras/render/taxonomy_intra_doc_render.py
DELETED
|
@@ -1,182 +0,0 @@
|
|
| 1 |
-
"""Rendu HTML de la heatmap class × position — Sprint 76.
|
| 2 |
-
|
| 3 |
-
A.I.4 chantier 2 du plan d'évolution 2026.
|
| 4 |
-
|
| 5 |
-
Suite directe ``picarones/core/taxonomy_intra_doc.py``. Pattern
|
| 6 |
-
identique aux autres rendus (Sprints 41/43/62/67/72/74/75) :
|
| 7 |
-
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
-
|
| 9 |
-
Sortie typique
|
| 10 |
-
--------------
|
| 11 |
-
Une grille N_classes × N_bins où chaque cellule indique la densité
|
| 12 |
-
d'erreurs de cette classe à cette position dans le document.
|
| 13 |
-
Lecture immédiate : « ligature_error concentré dans la première
|
| 14 |
-
tranche → erreur de marge ; visual_confusion uniformément réparti
|
| 15 |
-
→ erreur de scribe ».
|
| 16 |
-
|
| 17 |
-
Adaptive : si ``data is None`` ou si toutes les classes ont 0
|
| 18 |
-
erreur, retourne ``""``.
|
| 19 |
-
"""
|
| 20 |
-
|
| 21 |
-
from __future__ import annotations
|
| 22 |
-
|
| 23 |
-
from html import escape as _e
|
| 24 |
-
from typing import Optional
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
def _color_for_density(density: float) -> str:
|
| 28 |
-
"""Gradient blanc → orange profond pour densité ∈ [0, 1].
|
| 29 |
-
|
| 30 |
-
Interpolation entre #ffffff (0) et #c2410c (1).
|
| 31 |
-
"""
|
| 32 |
-
f = max(0.0, min(1.0, density))
|
| 33 |
-
r = int(255 + (194 - 255) * f)
|
| 34 |
-
g = int(255 + (65 - 255) * f)
|
| 35 |
-
b = int(255 + (12 - 255) * f)
|
| 36 |
-
return f"#{r:02x}{g:02x}{b:02x}"
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
def _text_color_for_bg(density: float) -> str:
|
| 40 |
-
return "#fff" if density > 0.55 else "#222"
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
def _build_heatmap_svg(
|
| 44 |
-
classes_with_errors: list[str],
|
| 45 |
-
per_class: dict[str, list[int]],
|
| 46 |
-
n_bins: int,
|
| 47 |
-
*,
|
| 48 |
-
cell_w: int = 36,
|
| 49 |
-
cell_h: int = 26,
|
| 50 |
-
label_left: int = 150,
|
| 51 |
-
label_top: int = 30,
|
| 52 |
-
) -> str:
|
| 53 |
-
"""Construit la heatmap SVG class × position."""
|
| 54 |
-
n_rows = len(classes_with_errors)
|
| 55 |
-
if n_rows == 0:
|
| 56 |
-
return ""
|
| 57 |
-
width = label_left + n_bins * cell_w + 10
|
| 58 |
-
height = label_top + n_rows * cell_h + 30 # +30 pour étiquette X
|
| 59 |
-
|
| 60 |
-
# Normalisation : pour chaque classe, densité relative au max
|
| 61 |
-
# de cette classe (mise en évidence des positions concentrées).
|
| 62 |
-
parts = [
|
| 63 |
-
f'<svg xmlns="http://www.w3.org/2000/svg" '
|
| 64 |
-
f'width="{width}" height="{height}" '
|
| 65 |
-
f'viewBox="0 0 {width} {height}" '
|
| 66 |
-
f'role="img" aria-label="Heatmap class taxonomique × position">',
|
| 67 |
-
]
|
| 68 |
-
# Étiquettes des colonnes (positions)
|
| 69 |
-
for j in range(n_bins):
|
| 70 |
-
cx = label_left + j * cell_w + cell_w // 2
|
| 71 |
-
cy = label_top - 6
|
| 72 |
-
parts.append(
|
| 73 |
-
f'<text x="{cx}" y="{cy}" '
|
| 74 |
-
f'font-size="10" fill="#666" text-anchor="middle">'
|
| 75 |
-
f'{j + 1}</text>'
|
| 76 |
-
)
|
| 77 |
-
# Cellules
|
| 78 |
-
for i, cls in enumerate(classes_with_errors):
|
| 79 |
-
# Étiquette de ligne (classe)
|
| 80 |
-
rx = label_left - 6
|
| 81 |
-
ry = label_top + i * cell_h + cell_h // 2 + 4
|
| 82 |
-
parts.append(
|
| 83 |
-
f'<text x="{rx}" y="{ry}" '
|
| 84 |
-
f'font-size="11" fill="#333" text-anchor="end">'
|
| 85 |
-
f'{_e(cls)}</text>'
|
| 86 |
-
)
|
| 87 |
-
counts = per_class.get(cls, [0] * n_bins)
|
| 88 |
-
max_count = max(counts) if counts else 0
|
| 89 |
-
for j in range(n_bins):
|
| 90 |
-
x = label_left + j * cell_w
|
| 91 |
-
y = label_top + i * cell_h
|
| 92 |
-
count = counts[j] if j < len(counts) else 0
|
| 93 |
-
density = (count / max_count) if max_count > 0 else 0.0
|
| 94 |
-
color = _color_for_density(density)
|
| 95 |
-
text_color = _text_color_for_bg(density)
|
| 96 |
-
parts.append(
|
| 97 |
-
f'<rect x="{x}" y="{y}" '
|
| 98 |
-
f'width="{cell_w}" height="{cell_h}" '
|
| 99 |
-
f'fill="{color}" stroke="#ddd" stroke-width="0.5"/>'
|
| 100 |
-
)
|
| 101 |
-
if count > 0:
|
| 102 |
-
parts.append(
|
| 103 |
-
f'<text x="{x + cell_w // 2}" '
|
| 104 |
-
f'y="{y + cell_h // 2 + 4}" '
|
| 105 |
-
f'font-size="10" fill="{text_color}" '
|
| 106 |
-
f'text-anchor="middle">{count}</text>'
|
| 107 |
-
)
|
| 108 |
-
# Étiquette axe X en bas
|
| 109 |
-
cx_axis = label_left + (n_bins * cell_w) // 2
|
| 110 |
-
cy_axis = height - 6
|
| 111 |
-
parts.append(
|
| 112 |
-
f'<text x="{cx_axis}" y="{cy_axis}" '
|
| 113 |
-
f'font-size="11" fill="#666" text-anchor="middle" '
|
| 114 |
-
f'font-style="italic">'
|
| 115 |
-
f'Position dans le document (1 = début)</text>'
|
| 116 |
-
)
|
| 117 |
-
parts.append("</svg>")
|
| 118 |
-
return "".join(parts)
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
def build_taxonomy_intra_doc_html(
|
| 122 |
-
data: Optional[dict],
|
| 123 |
-
labels: Optional[dict[str, str]] = None,
|
| 124 |
-
) -> str:
|
| 125 |
-
"""Construit le bloc HTML complet de la heatmap intra-document.
|
| 126 |
-
|
| 127 |
-
Retourne ``""`` si ``data is None`` ou aucune erreur.
|
| 128 |
-
"""
|
| 129 |
-
if not data:
|
| 130 |
-
return ""
|
| 131 |
-
n_bins = data.get("n_bins", 0)
|
| 132 |
-
per_class = data.get("per_class") or {}
|
| 133 |
-
total_errors = data.get("total_errors", 0)
|
| 134 |
-
if total_errors == 0 or n_bins <= 0:
|
| 135 |
-
return ""
|
| 136 |
-
# Filtre : uniquement les classes ayant au moins une erreur
|
| 137 |
-
classes_with_errors = [
|
| 138 |
-
cls for cls, counts in per_class.items()
|
| 139 |
-
if isinstance(counts, list) and sum(counts) > 0
|
| 140 |
-
]
|
| 141 |
-
if not classes_with_errors:
|
| 142 |
-
return ""
|
| 143 |
-
|
| 144 |
-
labels = labels or {}
|
| 145 |
-
title = labels.get(
|
| 146 |
-
"intradoc_title",
|
| 147 |
-
"Évolution intra-document des classes d'erreur",
|
| 148 |
-
)
|
| 149 |
-
note = labels.get(
|
| 150 |
-
"intradoc_note",
|
| 151 |
-
"Heatmap class × position : densité relative par classe "
|
| 152 |
-
"(plus foncé = concentré). Une classe concentrée dans la "
|
| 153 |
-
"première colonne suggère une erreur de marge ; "
|
| 154 |
-
"une distribution uniforme suggère une erreur de scribe.",
|
| 155 |
-
)
|
| 156 |
-
n_words_gt = data.get("n_words_gt", 0)
|
| 157 |
-
n_words_template = labels.get(
|
| 158 |
-
"intradoc_n_words",
|
| 159 |
-
"Calculé sur {n_words_gt} mots GT, répartis en {n_bins} tranches.",
|
| 160 |
-
)
|
| 161 |
-
n_words_phrase = n_words_template.format(
|
| 162 |
-
n_words_gt=n_words_gt, n_bins=n_bins,
|
| 163 |
-
)
|
| 164 |
-
|
| 165 |
-
svg = _build_heatmap_svg(classes_with_errors, per_class, n_bins)
|
| 166 |
-
|
| 167 |
-
parts = [
|
| 168 |
-
'<div class="intradoc" style="margin:1rem 0">',
|
| 169 |
-
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 170 |
-
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 171 |
-
f'{_e(note)}</div>',
|
| 172 |
-
f'<div style="font-size:.8rem;opacity:.7;margin-bottom:.5rem">'
|
| 173 |
-
f'{_e(n_words_phrase)}</div>',
|
| 174 |
-
svg,
|
| 175 |
-
"</div>",
|
| 176 |
-
]
|
| 177 |
-
return "".join(parts)
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
__all__ = [
|
| 181 |
-
"build_taxonomy_intra_doc_html",
|
| 182 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
picarones/report/image_predictive_render.py
CHANGED
|
@@ -1,26 +1,221 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
aux
|
| 5 |
-
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Rendu HTML « Profil d'image du corpus » — Sprint 93 (A.II.7).
|
| 2 |
|
| 3 |
+
Suite directe ``picarones/core/image_predictive.py``. Pattern
|
| 4 |
+
identique aux autres rendus : server-side, pas de JS, anti-
|
| 5 |
+
injection systématique.
|
| 6 |
|
| 7 |
+
Vue
|
| 8 |
+
---
|
| 9 |
+
Deux blocs dans une section unique :
|
| 10 |
+
|
| 11 |
+
1. **Complexité paléographique** : moyenne, médiane, min, max,
|
| 12 |
+
écart-type sur l'ensemble du corpus.
|
| 13 |
+
2. **Homogénéité du corpus** : score combiné + détail par
|
| 14 |
+
feature (mean, stdev, contribution normalisée).
|
| 15 |
+
|
| 16 |
+
Adaptive : ``""`` si pas de données.
|
| 17 |
+
|
| 18 |
+
Note d'intégration
|
| 19 |
+
------------------
|
| 20 |
+
Module pur — l'utilisateur compose :
|
| 21 |
+
|
| 22 |
+
.. code-block:: python
|
| 23 |
+
|
| 24 |
+
from picarones.measurements.image_predictive import aggregate_corpus_predictive
|
| 25 |
+
from picarones.report.image_predictive_render import (
|
| 26 |
+
build_image_predictive_html,
|
| 27 |
+
)
|
| 28 |
+
|
| 29 |
+
qualities = [doc.image_quality.as_dict() for doc in benchmark.docs]
|
| 30 |
+
agg = aggregate_corpus_predictive(qualities)
|
| 31 |
+
html = build_image_predictive_html(agg, labels)
|
| 32 |
"""
|
| 33 |
|
| 34 |
+
from __future__ import annotations
|
| 35 |
+
|
| 36 |
+
from html import escape as _e
|
| 37 |
+
from typing import Optional
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
def _color_for_score(score: float) -> str:
|
| 41 |
+
"""Vert (faible) → orange → rouge (élevé)."""
|
| 42 |
+
f = max(0.0, min(1.0, score))
|
| 43 |
+
if f < 0.5:
|
| 44 |
+
t = f / 0.5
|
| 45 |
+
r = int(167 + (235 - 167) * t)
|
| 46 |
+
g = int(240 + (180 - 240) * t)
|
| 47 |
+
b = int(167 + (60 - 167) * t)
|
| 48 |
+
else:
|
| 49 |
+
t = (f - 0.5) / 0.5
|
| 50 |
+
r = int(235 + (220 - 235) * t)
|
| 51 |
+
g = int(180 + (50 - 180) * t)
|
| 52 |
+
b = int(60 + (50 - 60) * t)
|
| 53 |
+
return f"#{r:02x}{g:02x}{b:02x}"
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
_FEATURE_LABEL_KEYS = {
|
| 57 |
+
"noise_level": "imgpred_feat_noise",
|
| 58 |
+
"sharpness_score": "imgpred_feat_sharpness",
|
| 59 |
+
"contrast_score": "imgpred_feat_contrast",
|
| 60 |
+
"rotation_degrees": "imgpred_feat_rotation",
|
| 61 |
+
}
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
def _render_complexity_block(
|
| 65 |
+
aggregated: dict, labels: dict[str, str],
|
| 66 |
+
) -> str:
|
| 67 |
+
h_complex = labels.get(
|
| 68 |
+
"imgpred_complexity", "Complexité paléographique",
|
| 69 |
+
)
|
| 70 |
+
h_mean = labels.get("imgpred_mean", "Moyenne")
|
| 71 |
+
h_median = labels.get("imgpred_median", "Médiane")
|
| 72 |
+
h_min = labels.get("imgpred_min", "Min")
|
| 73 |
+
h_max = labels.get("imgpred_max", "Max")
|
| 74 |
+
h_stdev = labels.get("imgpred_stdev", "Écart-type")
|
| 75 |
+
h_docs = labels.get("imgpred_docs", "Docs")
|
| 76 |
+
mean = float(aggregated.get("complexity_mean") or 0.0)
|
| 77 |
+
median = float(aggregated.get("complexity_median") or 0.0)
|
| 78 |
+
mn = float(aggregated.get("complexity_min") or 0.0)
|
| 79 |
+
mx = float(aggregated.get("complexity_max") or 0.0)
|
| 80 |
+
sd = float(aggregated.get("complexity_stdev") or 0.0)
|
| 81 |
+
n_docs = int(aggregated.get("n_docs") or 0)
|
| 82 |
+
color_mean = _color_for_score(mean)
|
| 83 |
+
return (
|
| 84 |
+
f'<div style="font-weight:600;margin:.4rem 0 .3rem 0">'
|
| 85 |
+
f'{_e(h_complex)}</div>'
|
| 86 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 87 |
+
'font-size:.9rem;margin-bottom:.8rem">'
|
| 88 |
+
f'<thead><tr>'
|
| 89 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 90 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_mean)}</th>'
|
| 91 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 92 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_median)}</th>'
|
| 93 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 94 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_min)}</th>'
|
| 95 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 96 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_max)}</th>'
|
| 97 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 98 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_stdev)}</th>'
|
| 99 |
+
f'<th style="padding:.4rem .6rem;text-align:right;'
|
| 100 |
+
f'border-bottom:1px solid #ccc;font-weight:600">{_e(h_docs)}</th>'
|
| 101 |
+
f'</tr></thead>'
|
| 102 |
+
f'<tbody><tr>'
|
| 103 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 104 |
+
f'background:{color_mean};font-family:monospace;font-weight:600">'
|
| 105 |
+
f'{mean:.3f}</td>'
|
| 106 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 107 |
+
f'font-family:monospace">{median:.3f}</td>'
|
| 108 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 109 |
+
f'font-family:monospace">{mn:.3f}</td>'
|
| 110 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 111 |
+
f'font-family:monospace">{mx:.3f}</td>'
|
| 112 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 113 |
+
f'font-family:monospace">{sd:.3f}</td>'
|
| 114 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 115 |
+
f'font-family:monospace">{n_docs}</td>'
|
| 116 |
+
f'</tr></tbody></table>'
|
| 117 |
+
)
|
| 118 |
+
|
| 119 |
+
|
| 120 |
+
def _render_homogeneity_block(
|
| 121 |
+
homogeneity: dict, labels: dict[str, str],
|
| 122 |
+
) -> str:
|
| 123 |
+
h_homo = labels.get(
|
| 124 |
+
"imgpred_homogeneity", "Homogénéité du corpus",
|
| 125 |
+
)
|
| 126 |
+
h_feat = labels.get("imgpred_feature", "Feature")
|
| 127 |
+
h_mean = labels.get("imgpred_feat_mean", "Moyenne")
|
| 128 |
+
h_stdev = labels.get("imgpred_feat_stdev", "Écart-type")
|
| 129 |
+
h_norm = labels.get(
|
| 130 |
+
"imgpred_feat_norm", "Contribution normalisée",
|
| 131 |
+
)
|
| 132 |
+
score = float(homogeneity.get("score") or 0.0)
|
| 133 |
+
color = _color_for_score(score)
|
| 134 |
+
parts = [
|
| 135 |
+
f'<div style="font-weight:600;margin:.4rem 0 .3rem 0">'
|
| 136 |
+
f'{_e(h_homo)} : '
|
| 137 |
+
f'<span style="background:{color};padding:.1rem .4rem;'
|
| 138 |
+
f'border-radius:.3rem;font-family:monospace">{score:.3f}</span>'
|
| 139 |
+
f'</div>',
|
| 140 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 141 |
+
'font-size:.9rem">',
|
| 142 |
+
'<thead><tr>',
|
| 143 |
+
]
|
| 144 |
+
for col in (h_feat, h_mean, h_stdev, h_norm):
|
| 145 |
+
parts.append(
|
| 146 |
+
f'<th style="padding:.4rem .6rem;text-align:left;'
|
| 147 |
+
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 148 |
+
f'{_e(col)}</th>'
|
| 149 |
+
)
|
| 150 |
+
parts.append("</tr></thead><tbody>")
|
| 151 |
+
per_feat = homogeneity.get("per_feature") or {}
|
| 152 |
+
for key, label_key in _FEATURE_LABEL_KEYS.items():
|
| 153 |
+
if key not in per_feat:
|
| 154 |
+
continue
|
| 155 |
+
slot = per_feat[key]
|
| 156 |
+
feat_label = labels.get(label_key, key)
|
| 157 |
+
feat_mean = float(slot.get("mean") or 0.0)
|
| 158 |
+
feat_stdev = float(slot.get("stdev") or 0.0)
|
| 159 |
+
feat_norm = float(slot.get("normalised") or 0.0)
|
| 160 |
+
norm_color = _color_for_score(feat_norm)
|
| 161 |
+
parts.append(
|
| 162 |
+
f'<tr>'
|
| 163 |
+
f'<td style="padding:.4rem .6rem">{_e(feat_label)}</td>'
|
| 164 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 165 |
+
f'font-family:monospace">{feat_mean:.3f}</td>'
|
| 166 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 167 |
+
f'font-family:monospace">{feat_stdev:.3f}</td>'
|
| 168 |
+
f'<td style="padding:.4rem .6rem;text-align:right;'
|
| 169 |
+
f'background:{norm_color};font-family:monospace">'
|
| 170 |
+
f'{feat_norm:.3f}</td>'
|
| 171 |
+
f'</tr>'
|
| 172 |
+
)
|
| 173 |
+
parts.append("</tbody></table>")
|
| 174 |
+
return "".join(parts)
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
def build_image_predictive_html(
|
| 178 |
+
aggregated: Optional[dict],
|
| 179 |
+
labels: Optional[dict[str, str]] = None,
|
| 180 |
+
) -> str:
|
| 181 |
+
"""Construit la vue HTML « Profil d'image du corpus ».
|
| 182 |
+
|
| 183 |
+
Parameters
|
| 184 |
+
----------
|
| 185 |
+
aggregated:
|
| 186 |
+
Sortie de ``aggregate_corpus_predictive``. Si ``None``
|
| 187 |
+
ou ``n_docs == 0``, retourne ``""``.
|
| 188 |
+
labels:
|
| 189 |
+
Dict i18n. Clés sous le préfixe ``imgpred_*``.
|
| 190 |
+
"""
|
| 191 |
+
if not aggregated:
|
| 192 |
+
return ""
|
| 193 |
+
if not aggregated.get("n_docs"):
|
| 194 |
+
return ""
|
| 195 |
+
labels = labels or {}
|
| 196 |
+
title = labels.get(
|
| 197 |
+
"imgpred_title", "Profil d'image du corpus",
|
| 198 |
+
)
|
| 199 |
+
note = labels.get(
|
| 200 |
+
"imgpred_note",
|
| 201 |
+
"Score de complexité paléographique combinant bruit, "
|
| 202 |
+
"flou, faible contraste et rotation. Le score "
|
| 203 |
+
"d'homogénéité signale si la moyenne globale est fiable "
|
| 204 |
+
"(corpus uniforme) ou trompeuse (corpus hétérogène — "
|
| 205 |
+
"voir alors la vue stratifiée).",
|
| 206 |
+
)
|
| 207 |
+
parts = [
|
| 208 |
+
'<section class="imgpred-section" style="margin:1rem 0">',
|
| 209 |
+
f'<h3 style="margin:0 0 .3rem 0">{_e(title)}</h3>',
|
| 210 |
+
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.6rem">'
|
| 211 |
+
f'{_e(note)}</div>',
|
| 212 |
+
]
|
| 213 |
+
parts.append(_render_complexity_block(aggregated, labels))
|
| 214 |
+
homo = aggregated.get("homogeneity")
|
| 215 |
+
if isinstance(homo, dict):
|
| 216 |
+
parts.append(_render_homogeneity_block(homo, labels))
|
| 217 |
+
parts.append("</section>")
|
| 218 |
+
return "".join(parts)
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
__all__ = ["build_image_predictive_html"]
|
picarones/report/lexical_modernization_render.py
CHANGED
|
@@ -1,26 +1,119 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
aux imports historiques (y compris les noms privés ``_*``) de
|
| 5 |
-
continuer à fonctionner sans modification.
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
-
# Réexport explicite de TOUS les noms (privés inclus) pour la
|
| 13 |
-
# rétrocompatibilité des tests Sprints qui importent ``_helper``,
|
| 14 |
-
# ``_compute_X``, ``_SCIPY_AVAILABLE``, etc. Sans cette boucle, ``import *``
|
| 15 |
-
# ne propage que les noms publics et casse les imports historiques.
|
| 16 |
-
import picarones.extras.render.lexical_modernization_render as _shim_module
|
| 17 |
-
for _shim_name in dir(_shim_module):
|
| 18 |
-
if _shim_name == "__builtins__":
|
| 19 |
-
continue
|
| 20 |
-
if _shim_name not in globals():
|
| 21 |
-
globals()[_shim_name] = getattr(_shim_module, _shim_name)
|
| 22 |
-
del _shim_module, _shim_name
|
| 23 |
|
| 24 |
__all__ = [
|
| 25 |
-
|
| 26 |
]
|
|
|
|
| 1 |
+
"""Rendu HTML de la vue « Modernisation lexicale » — Sprint 80.
|
| 2 |
|
| 3 |
+
A.I.7 du plan d'évolution 2026.
|
|
|
|
|
|
|
| 4 |
|
| 5 |
+
Suite directe ``picarones/core/lexical_modernization.py``.
|
| 6 |
+
Pattern identique aux autres rendus (Sprints 41/43/62/67/72/74/75/76/77) :
|
| 7 |
+
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
+
|
| 9 |
+
Vue
|
| 10 |
+
---
|
| 11 |
+
Tableau trié par taux de modernisation décroissant : forme
|
| 12 |
+
historique GT → forme(s) modernisée(s), occurrences GT, %.
|
| 13 |
+
Couleur de cellule pour le %.
|
| 14 |
"""
|
| 15 |
|
| 16 |
+
from __future__ import annotations
|
| 17 |
+
|
| 18 |
+
from html import escape as _e
|
| 19 |
+
from typing import Optional
|
| 20 |
+
|
| 21 |
+
from picarones.measurements.lexical_modernization import top_modernized_tokens
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
def _color_for_rate(rate: float) -> str:
|
| 25 |
+
"""Gradient blanc → orange profond pour rate ∈ [0, 1]."""
|
| 26 |
+
f = max(0.0, min(1.0, rate))
|
| 27 |
+
r = int(255 + (194 - 255) * f)
|
| 28 |
+
g = int(255 + (65 - 255) * f)
|
| 29 |
+
b = int(255 + (12 - 255) * f)
|
| 30 |
+
return f"#{r:02x}{g:02x}{b:02x}"
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
def _format_variants(variants: dict, max_show: int = 3) -> str:
|
| 34 |
+
"""Liste compacte des variants modernisés."""
|
| 35 |
+
items = sorted(variants.items(), key=lambda kv: -kv[1])
|
| 36 |
+
shown = items[:max_show]
|
| 37 |
+
rest = len(items) - max_show
|
| 38 |
+
parts = [
|
| 39 |
+
f"{_e(form)} ({count})"
|
| 40 |
+
for form, count in shown
|
| 41 |
+
]
|
| 42 |
+
if rest > 0:
|
| 43 |
+
parts.append(f"+{rest}")
|
| 44 |
+
return ", ".join(parts)
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
def build_lexical_modernization_html(
|
| 48 |
+
data: Optional[dict],
|
| 49 |
+
labels: Optional[dict[str, str]] = None,
|
| 50 |
+
*,
|
| 51 |
+
top_n: int = 20,
|
| 52 |
+
min_total: int = 1,
|
| 53 |
+
) -> str:
|
| 54 |
+
"""Construit la table HTML de modernisation lexicale.
|
| 55 |
+
|
| 56 |
+
Retourne ``""`` si ``data is None`` ou si aucun token modernisé.
|
| 57 |
+
"""
|
| 58 |
+
if not data:
|
| 59 |
+
return ""
|
| 60 |
+
rows = top_modernized_tokens(data, n=top_n, min_total=min_total)
|
| 61 |
+
if not rows:
|
| 62 |
+
return ""
|
| 63 |
+
labels = labels or {}
|
| 64 |
+
title = labels.get(
|
| 65 |
+
"lexmod_title", "Modernisation lexicale (top tokens)",
|
| 66 |
+
)
|
| 67 |
+
note = labels.get(
|
| 68 |
+
"lexmod_note",
|
| 69 |
+
"Tokens GT que le moteur réécrit le plus souvent. "
|
| 70 |
+
"Lecture : « maistre → maître modernisé dans 85 % des cas » "
|
| 71 |
+
"indique de quoi corriger dans le prompt pour préserver "
|
| 72 |
+
"l'orthographe historique.",
|
| 73 |
+
)
|
| 74 |
+
gt_label = labels.get("lexmod_gt_label", "Forme historique GT")
|
| 75 |
+
hyp_label = labels.get("lexmod_hyp_label", "Variantes OCR")
|
| 76 |
+
n_label = labels.get("lexmod_n_label", "n GT")
|
| 77 |
+
rate_label = labels.get("lexmod_rate_label", "% modernisé")
|
| 78 |
+
|
| 79 |
+
parts = [
|
| 80 |
+
'<div class="lexmod" style="margin:1rem 0">',
|
| 81 |
+
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 82 |
+
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 83 |
+
f'{_e(note)}</div>',
|
| 84 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 85 |
+
'font-size:.85rem">',
|
| 86 |
+
'<thead><tr>',
|
| 87 |
+
]
|
| 88 |
+
for col in (gt_label, hyp_label, n_label, rate_label):
|
| 89 |
+
parts.append(
|
| 90 |
+
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 91 |
+
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 92 |
+
f'{_e(col)}</th>'
|
| 93 |
+
)
|
| 94 |
+
parts.append("</tr></thead><tbody>")
|
| 95 |
+
for gt_token, slot in rows:
|
| 96 |
+
rate = slot.get("rate_modernized", 0.0)
|
| 97 |
+
n_total = slot.get("n_total", 0)
|
| 98 |
+
variants_str = _format_variants(slot.get("variants") or {})
|
| 99 |
+
rate_color = _color_for_rate(rate)
|
| 100 |
+
parts.append(
|
| 101 |
+
f'<tr>'
|
| 102 |
+
f'<td style="padding:.3rem .5rem;font-family:monospace">'
|
| 103 |
+
f'{_e(gt_token)}</td>'
|
| 104 |
+
f'<td style="padding:.3rem .5rem;font-size:.85rem">'
|
| 105 |
+
f'{variants_str}</td>'
|
| 106 |
+
f'<td style="padding:.3rem .5rem;text-align:right;'
|
| 107 |
+
f'font-family:monospace">{n_total}</td>'
|
| 108 |
+
f'<td style="padding:.3rem .5rem;text-align:right;'
|
| 109 |
+
f'background:{rate_color};font-family:monospace">'
|
| 110 |
+
f'{rate * 100:.0f}%</td>'
|
| 111 |
+
f'</tr>'
|
| 112 |
+
)
|
| 113 |
+
parts.append("</tbody></table></div>")
|
| 114 |
+
return "".join(parts)
|
| 115 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 116 |
|
| 117 |
__all__ = [
|
| 118 |
+
"build_lexical_modernization_html",
|
| 119 |
]
|
picarones/report/module_audit_render.py
CHANGED
|
@@ -1,26 +1,173 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
aux
|
| 5 |
-
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
if
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Rendu HTML « Modules audités » — Sprint 97 (B.6).
|
| 2 |
|
| 3 |
+
Suite directe ``picarones/core/module_policy.py``. Pattern
|
| 4 |
+
identique aux autres rendus : server-side, pas de JS, anti-
|
| 5 |
+
injection systématique.
|
| 6 |
|
| 7 |
+
Vue
|
| 8 |
+
---
|
| 9 |
+
Tableau récapitulatif des modules utilisés dans une pipeline
|
| 10 |
+
composée, chacun avec :
|
| 11 |
+
|
| 12 |
+
- Statut d'audit (✓ vert si tous les checks passent, ✗ rouge
|
| 13 |
+
sinon, avec compte des échecs) ;
|
| 14 |
+
- Métadonnées : version, auteur, licence ;
|
| 15 |
+
- Citation académique si fournie ;
|
| 16 |
+
- Lien vers la homepage si fourni.
|
| 17 |
+
|
| 18 |
+
Adaptive : ``""`` si la liste est vide.
|
| 19 |
+
|
| 20 |
+
Note d'intégration
|
| 21 |
+
------------------
|
| 22 |
+
Module pur — l'utilisateur compose la liste depuis sa
|
| 23 |
+
``PipelineSpec`` augmentée des ``ModuleManifest`` :
|
| 24 |
+
|
| 25 |
+
.. code-block:: python
|
| 26 |
+
|
| 27 |
+
from picarones.measurements.module_policy import audit_module
|
| 28 |
+
from picarones.report.module_audit_render import build_module_audit_html
|
| 29 |
+
|
| 30 |
+
audits = []
|
| 31 |
+
for step in pipeline.steps:
|
| 32 |
+
manifest = step.module.manifest # convention applicative
|
| 33 |
+
result = audit_module(step.module, manifest)
|
| 34 |
+
audits.append({
|
| 35 |
+
"manifest": manifest.as_dict(),
|
| 36 |
+
"audit": result.as_dict(),
|
| 37 |
+
})
|
| 38 |
+
html = build_module_audit_html(audits, labels)
|
| 39 |
"""
|
| 40 |
|
| 41 |
+
from __future__ import annotations
|
| 42 |
+
|
| 43 |
+
from html import escape as _e
|
| 44 |
+
from typing import Optional
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
def _passed_badge(passed: bool, n_failed: int, label_pass: str,
|
| 48 |
+
label_fail: str) -> str:
|
| 49 |
+
if passed:
|
| 50 |
+
return (
|
| 51 |
+
f'<span style="color:#16a34a;font-weight:700">'
|
| 52 |
+
f'✓ {_e(label_pass)}</span>'
|
| 53 |
+
)
|
| 54 |
+
return (
|
| 55 |
+
f'<span style="color:#dc2626;font-weight:700">'
|
| 56 |
+
f'✗ {_e(label_fail)} ({n_failed})</span>'
|
| 57 |
+
)
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
def build_module_audit_html(
|
| 61 |
+
audits: Optional[list],
|
| 62 |
+
labels: Optional[dict[str, str]] = None,
|
| 63 |
+
) -> str:
|
| 64 |
+
"""Construit la vue HTML « Modules audités ».
|
| 65 |
+
|
| 66 |
+
Parameters
|
| 67 |
+
----------
|
| 68 |
+
audits:
|
| 69 |
+
Liste de dicts ``{"manifest": ManifestDict, "audit":
|
| 70 |
+
AuditResultDict}``. Si vide ou ``None``, retourne ``""``.
|
| 71 |
+
labels:
|
| 72 |
+
Dict i18n. Clés sous le préfixe ``audit_*``.
|
| 73 |
+
"""
|
| 74 |
+
if not audits:
|
| 75 |
+
return ""
|
| 76 |
+
rows = [
|
| 77 |
+
a for a in audits
|
| 78 |
+
if isinstance(a, dict)
|
| 79 |
+
and isinstance(a.get("manifest"), dict)
|
| 80 |
+
and isinstance(a.get("audit"), dict)
|
| 81 |
+
]
|
| 82 |
+
if not rows:
|
| 83 |
+
return ""
|
| 84 |
+
labels = labels or {}
|
| 85 |
+
title = labels.get("audit_title", "Modules audités")
|
| 86 |
+
note = labels.get(
|
| 87 |
+
"audit_note",
|
| 88 |
+
"Récapitulatif des modules utilisés dans la pipeline "
|
| 89 |
+
"composée. Un module qui ne passe pas l'audit n'est "
|
| 90 |
+
"pas exécutable. Métadonnées issues du manifest fourni "
|
| 91 |
+
"par le contributeur (auteur, licence, citation).",
|
| 92 |
+
)
|
| 93 |
+
label_pass = labels.get("audit_pass", "audit OK")
|
| 94 |
+
label_fail = labels.get("audit_fail", "checks échoués")
|
| 95 |
+
h_module = labels.get("audit_module", "Module")
|
| 96 |
+
h_status = labels.get("audit_status", "Audit")
|
| 97 |
+
h_version = labels.get("audit_version", "Version")
|
| 98 |
+
h_author = labels.get("audit_author", "Auteur")
|
| 99 |
+
h_license = labels.get("audit_license", "Licence")
|
| 100 |
+
h_io = labels.get("audit_io", "Entrée → sortie")
|
| 101 |
+
h_citation = labels.get("audit_citation", "Citation")
|
| 102 |
+
h_homepage = labels.get("audit_homepage", "Page projet")
|
| 103 |
+
|
| 104 |
+
parts = [
|
| 105 |
+
'<section class="audit-section" style="margin:1rem 0">',
|
| 106 |
+
f'<h3 style="margin:0 0 .3rem 0">{_e(title)}</h3>',
|
| 107 |
+
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 108 |
+
f'{_e(note)}</div>',
|
| 109 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 110 |
+
'font-size:.9rem">',
|
| 111 |
+
'<thead><tr>',
|
| 112 |
+
]
|
| 113 |
+
for col in (h_module, h_status, h_version, h_author,
|
| 114 |
+
h_license, h_io, h_citation, h_homepage):
|
| 115 |
+
parts.append(
|
| 116 |
+
f'<th style="padding:.4rem .6rem;text-align:left;'
|
| 117 |
+
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 118 |
+
f'{_e(col)}</th>'
|
| 119 |
+
)
|
| 120 |
+
parts.append("</tr></thead><tbody>")
|
| 121 |
+
|
| 122 |
+
for entry in rows:
|
| 123 |
+
manifest = entry["manifest"]
|
| 124 |
+
audit = entry["audit"]
|
| 125 |
+
name = str(manifest.get("name") or "?")
|
| 126 |
+
version = str(manifest.get("version") or "—")
|
| 127 |
+
author = str(manifest.get("author") or "—")
|
| 128 |
+
license_ = str(manifest.get("license") or "—")
|
| 129 |
+
in_types = ", ".join(manifest.get("input_types") or []) or "—"
|
| 130 |
+
out_types = ", ".join(manifest.get("output_types") or []) or "—"
|
| 131 |
+
citation = manifest.get("citation") or ""
|
| 132 |
+
homepage = manifest.get("homepage") or ""
|
| 133 |
+
passed = bool(audit.get("passed"))
|
| 134 |
+
n_failed = int(audit.get("n_failed") or 0)
|
| 135 |
+
status_cell = _passed_badge(
|
| 136 |
+
passed, n_failed, label_pass, label_fail,
|
| 137 |
+
)
|
| 138 |
+
# Citation : tronqué si trop long
|
| 139 |
+
citation_str = str(citation)[:120]
|
| 140 |
+
if len(str(citation)) > 120:
|
| 141 |
+
citation_str += "…"
|
| 142 |
+
citation_cell = (
|
| 143 |
+
_e(citation_str) if citation_str.strip() else "—"
|
| 144 |
+
)
|
| 145 |
+
# Homepage : on n'auto-link **pas** (anti-injection +
|
| 146 |
+
# honnêteté : l'URL peut pointer ailleurs). On affiche
|
| 147 |
+
# le texte échappé tel quel.
|
| 148 |
+
homepage_cell = (
|
| 149 |
+
_e(str(homepage))[:80] + ("…" if len(str(homepage)) > 80 else "")
|
| 150 |
+
) if str(homepage).strip() else "—"
|
| 151 |
+
parts.append(
|
| 152 |
+
f'<tr>'
|
| 153 |
+
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 154 |
+
f'{_e(name)}</td>'
|
| 155 |
+
f'<td style="padding:.4rem .6rem">{status_cell}</td>'
|
| 156 |
+
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 157 |
+
f'{_e(version)}</td>'
|
| 158 |
+
f'<td style="padding:.4rem .6rem">{_e(author)}</td>'
|
| 159 |
+
f'<td style="padding:.4rem .6rem;font-family:monospace">'
|
| 160 |
+
f'{_e(license_)}</td>'
|
| 161 |
+
f'<td style="padding:.4rem .6rem;font-family:monospace;'
|
| 162 |
+
f'font-size:.8rem">{_e(in_types)} → {_e(out_types)}</td>'
|
| 163 |
+
f'<td style="padding:.4rem .6rem;font-size:.8rem;'
|
| 164 |
+
f'opacity:.85">{citation_cell}</td>'
|
| 165 |
+
f'<td style="padding:.4rem .6rem;font-family:monospace;'
|
| 166 |
+
f'font-size:.8rem">{homepage_cell}</td>'
|
| 167 |
+
f'</tr>'
|
| 168 |
+
)
|
| 169 |
+
parts.append("</tbody></table></section>")
|
| 170 |
+
return "".join(parts)
|
| 171 |
+
|
| 172 |
+
|
| 173 |
+
__all__ = ["build_module_audit_html"]
|
picarones/report/philological_render.py
CHANGED
|
@@ -1,26 +1,615 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
-
# Réexport explicite de TOUS les noms (privés inclus) pour la
|
| 13 |
-
# rétrocompatibilité des tests Sprints qui importent ``_helper``,
|
| 14 |
-
# ``_compute_X``, ``_SCIPY_AVAILABLE``, etc. Sans cette boucle, ``import *``
|
| 15 |
-
# ne propage que les noms publics et casse les imports historiques.
|
| 16 |
-
import picarones.extras.render.philological_render as _shim_module
|
| 17 |
-
for _shim_name in dir(_shim_module):
|
| 18 |
-
if _shim_name == "__builtins__":
|
| 19 |
-
continue
|
| 20 |
-
if _shim_name not in globals():
|
| 21 |
-
globals()[_shim_name] = getattr(_shim_module, _shim_name)
|
| 22 |
-
del _shim_module, _shim_name
|
| 23 |
|
| 24 |
__all__ = [
|
| 25 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
]
|
|
|
|
| 1 |
+
"""Rendu HTML server-side du profil philologique (Sprint 62).
|
| 2 |
|
| 3 |
+
Suite directe Sprint 61 (câblage backend) — produit les blocs HTML
|
| 4 |
+
qui exposent les six modules philologiques (Sprints 55-60) dans le
|
| 5 |
+
rapport :
|
| 6 |
|
| 7 |
+
- ``unicode_blocks`` (Sprint 55) — précision par bloc Unicode
|
| 8 |
+
- ``abbreviations`` (Sprint 56) — score strict + expansion par
|
| 9 |
+
abréviation médiévale Capelli
|
| 10 |
+
- ``mufi`` (Sprint 57) — couverture MUFI globale + par
|
| 11 |
+
caractère
|
| 12 |
+
- ``early_modern`` (Sprint 58) — préservation des marqueurs
|
| 13 |
+
typographiques imprimé ancien
|
| 14 |
+
- ``modern_archives`` (Sprint 59) — strict + expansion par
|
| 15 |
+
catégorie d'archive moderne
|
| 16 |
+
- ``roman_numerals`` (Sprint 60) — breakdown 5 statuts de
|
| 17 |
+
restitution
|
| 18 |
+
|
| 19 |
+
Principe identique aux Sprints 41 (NER) et 43 (calibration) :
|
| 20 |
+
|
| 21 |
+
- Rendu **server-side**, pas de JavaScript, déterministe.
|
| 22 |
+
- Section adaptive : si aucun moteur n'a de signal pour un module
|
| 23 |
+
donné, la sous-section est silencieusement omise.
|
| 24 |
+
- Si **aucun module** n'a de signal sur l'ensemble des moteurs,
|
| 25 |
+
``build_philological_profile_html`` retourne une chaîne vide et
|
| 26 |
+
le bloc complet n'apparaît pas dans la vue analyses.
|
| 27 |
+
- **Aucune classification automatique** : on affiche les chiffres
|
| 28 |
+
bruts par catégorie/bloc/statut, le chercheur juge lui-même la
|
| 29 |
+
convention adoptée.
|
| 30 |
+
- Anti-injection : tous les noms de moteurs, catégories, statuts,
|
| 31 |
+
caractères passent par ``html.escape`` avant insertion.
|
| 32 |
"""
|
| 33 |
|
| 34 |
+
from __future__ import annotations
|
| 35 |
+
|
| 36 |
+
from html import escape as _e
|
| 37 |
+
from typing import Optional
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 41 |
+
# Helpers de coloration
|
| 42 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
def _color_for_score(score: float) -> str:
|
| 46 |
+
"""Gradient rouge → jaune → vert proportionnel à ``score`` ∈ [0, 1].
|
| 47 |
+
|
| 48 |
+
Identique à ``ner_render._color_for_f1``. Les scores
|
| 49 |
+
philologiques (preservation, coverage, accuracy) suivent la même
|
| 50 |
+
sémantique « plus c'est haut, mieux c'est » donc le gradient
|
| 51 |
+
est valide.
|
| 52 |
+
"""
|
| 53 |
+
f = max(0.0, min(1.0, score))
|
| 54 |
+
if f <= 0.5:
|
| 55 |
+
ratio = f / 0.5
|
| 56 |
+
r = int(220 + (240 - 220) * ratio)
|
| 57 |
+
g = int(100 + (220 - 100) * ratio)
|
| 58 |
+
b = int(100 + (130 - 100) * ratio)
|
| 59 |
+
else:
|
| 60 |
+
ratio = (f - 0.5) / 0.5
|
| 61 |
+
r = int(240 + (130 - 240) * ratio)
|
| 62 |
+
g = int(220 + (200 - 220) * ratio)
|
| 63 |
+
b = int(130 + (130 - 130) * ratio)
|
| 64 |
+
return f"#{r:02x}{g:02x}{b:02x}"
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
def _engines_with_module(
|
| 68 |
+
engines_summary: list[dict], module: str,
|
| 69 |
+
) -> list[dict]:
|
| 70 |
+
"""Filtre les moteurs ayant des données pour le module donné."""
|
| 71 |
+
out: list[dict] = []
|
| 72 |
+
for eng in engines_summary:
|
| 73 |
+
agg = eng.get("aggregated_philological") or {}
|
| 74 |
+
if module in agg and agg[module]:
|
| 75 |
+
out.append(eng)
|
| 76 |
+
return out
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
def _score_cell(score: Optional[float], extra: str = "") -> str:
|
| 80 |
+
"""Rend une cellule colorée. ``None`` → cellule grise « — »."""
|
| 81 |
+
if score is None:
|
| 82 |
+
return (
|
| 83 |
+
'<td style="padding:.3rem .5rem;text-align:center;'
|
| 84 |
+
'background:#f0f0f0;color:#999">—</td>'
|
| 85 |
+
)
|
| 86 |
+
color = _color_for_score(score)
|
| 87 |
+
text = f"{score * 100:.1f}%"
|
| 88 |
+
if extra:
|
| 89 |
+
text += f" <span style=\"opacity:.6;font-size:.85em\">({_e(extra)})</span>"
|
| 90 |
+
return (
|
| 91 |
+
f'<td style="padding:.3rem .5rem;text-align:center;'
|
| 92 |
+
f'background:{color}">{text}</td>'
|
| 93 |
+
)
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
def _table_header(
|
| 97 |
+
columns: list[str], engine_label: str,
|
| 98 |
+
) -> str:
|
| 99 |
+
"""Construit l'entête d'un tableau moteur × colonnes."""
|
| 100 |
+
parts = [
|
| 101 |
+
'<thead><tr>',
|
| 102 |
+
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 103 |
+
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 104 |
+
f'{_e(engine_label)}</th>',
|
| 105 |
+
]
|
| 106 |
+
for col in columns:
|
| 107 |
+
parts.append(
|
| 108 |
+
f'<th style="padding:.3rem .5rem;text-align:center;'
|
| 109 |
+
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 110 |
+
f'{_e(col)}</th>'
|
| 111 |
+
)
|
| 112 |
+
parts.append('</tr></thead>')
|
| 113 |
+
return "".join(parts)
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
def _engine_label_cell(name: str) -> str:
|
| 117 |
+
return (
|
| 118 |
+
f'<td style="padding:.3rem .5rem;font-weight:500;'
|
| 119 |
+
f'border-bottom:1px solid var(--border-light)">{_e(name)}</td>'
|
| 120 |
+
)
|
| 121 |
+
|
| 122 |
+
|
| 123 |
+
def _section_open(title: str, note: str = "") -> str:
|
| 124 |
+
parts = [
|
| 125 |
+
'<div class="philological-section" '
|
| 126 |
+
'style="margin:1rem 0;padding:.75rem;'
|
| 127 |
+
'background:var(--bg-secondary);border-radius:6px">',
|
| 128 |
+
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 129 |
+
]
|
| 130 |
+
if note:
|
| 131 |
+
parts.append(
|
| 132 |
+
f'<div style="font-size:.8rem;opacity:.75;margin-bottom:.5rem">'
|
| 133 |
+
f'{_e(note)}</div>'
|
| 134 |
+
)
|
| 135 |
+
return "".join(parts)
|
| 136 |
+
|
| 137 |
+
|
| 138 |
+
def _section_close() -> str:
|
| 139 |
+
return "</div>"
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
def _table_open() -> str:
|
| 143 |
+
return (
|
| 144 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 145 |
+
'font-size:.85rem">'
|
| 146 |
+
)
|
| 147 |
+
|
| 148 |
+
|
| 149 |
+
def _table_close() -> str:
|
| 150 |
+
return "</table>"
|
| 151 |
+
|
| 152 |
+
|
| 153 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 154 |
+
# Sprint 55 — Précision par bloc Unicode
|
| 155 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
def build_unicode_blocks_section(
|
| 159 |
+
engines_summary: list[dict],
|
| 160 |
+
labels: Optional[dict[str, str]] = None,
|
| 161 |
+
) -> str:
|
| 162 |
+
relevant = _engines_with_module(engines_summary, "unicode_blocks")
|
| 163 |
+
if not relevant:
|
| 164 |
+
return ""
|
| 165 |
+
labels = labels or {}
|
| 166 |
+
title = labels.get(
|
| 167 |
+
"philo_unicode_blocks_title", "Précision par bloc Unicode",
|
| 168 |
+
)
|
| 169 |
+
note = labels.get(
|
| 170 |
+
"philo_unicode_blocks_note",
|
| 171 |
+
"Pourcentage de caractères correctement restitués par bloc "
|
| 172 |
+
"Unicode rencontré dans la GT (hors Basic Latin).",
|
| 173 |
+
)
|
| 174 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 175 |
+
global_label = labels.get("philo_global_label", "Global")
|
| 176 |
+
|
| 177 |
+
# Collecte tous les blocs présents (hors Basic Latin déjà filtré
|
| 178 |
+
# par adaptive masking, mais on défilte ici si Basic Latin
|
| 179 |
+
# apparaît malgré tout chez certains moteurs).
|
| 180 |
+
all_blocks: set[str] = set()
|
| 181 |
+
for eng in relevant:
|
| 182 |
+
per_block = eng["aggregated_philological"]["unicode_blocks"].get(
|
| 183 |
+
"per_block", {},
|
| 184 |
+
)
|
| 185 |
+
for block in per_block:
|
| 186 |
+
if block != "Basic Latin":
|
| 187 |
+
all_blocks.add(block)
|
| 188 |
+
blocks = sorted(all_blocks)
|
| 189 |
+
if not blocks:
|
| 190 |
+
return ""
|
| 191 |
+
|
| 192 |
+
parts = [_section_open(title, note), _table_open()]
|
| 193 |
+
parts.append(_table_header([global_label] + blocks, engine_label))
|
| 194 |
+
parts.append("<tbody>")
|
| 195 |
+
for eng in relevant:
|
| 196 |
+
agg = eng["aggregated_philological"]["unicode_blocks"]
|
| 197 |
+
global_acc = agg.get("global_accuracy", 0.0)
|
| 198 |
+
n_chars = agg.get("n_chars_total", 0)
|
| 199 |
+
parts.append("<tr>")
|
| 200 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 201 |
+
parts.append(_score_cell(global_acc, extra=f"n={n_chars}"))
|
| 202 |
+
per_block = agg.get("per_block", {})
|
| 203 |
+
for block in blocks:
|
| 204 |
+
stats = per_block.get(block)
|
| 205 |
+
if stats and stats.get("total", 0) > 0:
|
| 206 |
+
parts.append(_score_cell(
|
| 207 |
+
stats["accuracy"], extra=f"n={stats['total']}",
|
| 208 |
+
))
|
| 209 |
+
else:
|
| 210 |
+
parts.append(_score_cell(None))
|
| 211 |
+
parts.append("</tr>")
|
| 212 |
+
parts.append("</tbody>")
|
| 213 |
+
parts.append(_table_close())
|
| 214 |
+
parts.append(_section_close())
|
| 215 |
+
return "".join(parts)
|
| 216 |
+
|
| 217 |
+
|
| 218 |
+
# (sections suivantes définies plus loin)
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 222 |
+
# Sprint 56 — Abréviations Capelli médiévales
|
| 223 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
def build_abbreviations_section(
|
| 227 |
+
engines_summary: list[dict],
|
| 228 |
+
labels: Optional[dict[str, str]] = None,
|
| 229 |
+
) -> str:
|
| 230 |
+
relevant = _engines_with_module(engines_summary, "abbreviations")
|
| 231 |
+
if not relevant:
|
| 232 |
+
return ""
|
| 233 |
+
labels = labels or {}
|
| 234 |
+
title = labels.get(
|
| 235 |
+
"philo_abbreviations_title",
|
| 236 |
+
"Abréviations médiévales (Capelli)",
|
| 237 |
+
)
|
| 238 |
+
note = labels.get(
|
| 239 |
+
"philo_abbreviations_note",
|
| 240 |
+
"Strict = forme abrégée (ꝑ, ꝓ, ⁊…) préservée telle quelle ; "
|
| 241 |
+
"Expansion = abrégée OU forme développée (per, pro, et…) "
|
| 242 |
+
"présente. Le ratio strict/expansion par moteur indique la "
|
| 243 |
+
"convention adoptée (diplomatique / modernisante).",
|
| 244 |
+
)
|
| 245 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 246 |
+
strict_label = labels.get("philo_strict_label", "Strict")
|
| 247 |
+
expansion_label = labels.get("philo_expansion_label", "Expansion")
|
| 248 |
+
n_label = labels.get("philo_n_total_label", "n total")
|
| 249 |
+
|
| 250 |
+
parts = [_section_open(title, note), _table_open()]
|
| 251 |
+
parts.append(_table_header(
|
| 252 |
+
[strict_label, expansion_label, n_label], engine_label,
|
| 253 |
+
))
|
| 254 |
+
parts.append("<tbody>")
|
| 255 |
+
for eng in relevant:
|
| 256 |
+
agg = eng["aggregated_philological"]["abbreviations"]
|
| 257 |
+
parts.append("<tr>")
|
| 258 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 259 |
+
parts.append(_score_cell(agg.get("global_strict_score", 0.0)))
|
| 260 |
+
parts.append(_score_cell(agg.get("global_expansion_score", 0.0)))
|
| 261 |
+
parts.append(
|
| 262 |
+
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 263 |
+
f'{agg.get("n_abbreviations_in_reference", 0)}</td>'
|
| 264 |
+
)
|
| 265 |
+
parts.append("</tr>")
|
| 266 |
+
parts.append("</tbody>")
|
| 267 |
+
parts.append(_table_close())
|
| 268 |
+
parts.append(_section_close())
|
| 269 |
+
return "".join(parts)
|
| 270 |
+
|
| 271 |
+
|
| 272 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 273 |
+
# Sprint 57 — Couverture MUFI
|
| 274 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 275 |
+
|
| 276 |
+
|
| 277 |
+
def build_mufi_section(
|
| 278 |
+
engines_summary: list[dict],
|
| 279 |
+
labels: Optional[dict[str, str]] = None,
|
| 280 |
+
) -> str:
|
| 281 |
+
relevant = _engines_with_module(engines_summary, "mufi")
|
| 282 |
+
if not relevant:
|
| 283 |
+
return ""
|
| 284 |
+
labels = labels or {}
|
| 285 |
+
title = labels.get(
|
| 286 |
+
"philo_mufi_title",
|
| 287 |
+
"Couverture MUFI (Medieval Unicode Font Initiative)",
|
| 288 |
+
)
|
| 289 |
+
note = labels.get(
|
| 290 |
+
"philo_mufi_note",
|
| 291 |
+
"Taux de caractères MUFI de la GT (þ, ð, ƿ, ſ, æ, lettres "
|
| 292 |
+
"PUA…) correctement restitués dans l'OCR. Critère éditorial "
|
| 293 |
+
"central pour les médiévistes.",
|
| 294 |
+
)
|
| 295 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 296 |
+
coverage_label = labels.get("philo_mufi_coverage_label", "Couverture")
|
| 297 |
+
n_label = labels.get("philo_n_total_label", "n total")
|
| 298 |
+
|
| 299 |
+
parts = [_section_open(title, note), _table_open()]
|
| 300 |
+
parts.append(_table_header(
|
| 301 |
+
[coverage_label, n_label], engine_label,
|
| 302 |
+
))
|
| 303 |
+
parts.append("<tbody>")
|
| 304 |
+
for eng in relevant:
|
| 305 |
+
agg = eng["aggregated_philological"]["mufi"]
|
| 306 |
+
parts.append("<tr>")
|
| 307 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 308 |
+
parts.append(_score_cell(agg.get("coverage", 0.0)))
|
| 309 |
+
parts.append(
|
| 310 |
+
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 311 |
+
f'{agg.get("n_mufi_chars_reference", 0)}</td>'
|
| 312 |
+
)
|
| 313 |
+
parts.append("</tr>")
|
| 314 |
+
parts.append("</tbody>")
|
| 315 |
+
parts.append(_table_close())
|
| 316 |
+
parts.append(_section_close())
|
| 317 |
+
return "".join(parts)
|
| 318 |
+
|
| 319 |
+
|
| 320 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 321 |
+
# Sprint 58 — Marqueurs typographiques imprimé ancien (heatmap)
|
| 322 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def build_early_modern_section(
|
| 326 |
+
engines_summary: list[dict],
|
| 327 |
+
labels: Optional[dict[str, str]] = None,
|
| 328 |
+
) -> str:
|
| 329 |
+
relevant = _engines_with_module(engines_summary, "early_modern")
|
| 330 |
+
if not relevant:
|
| 331 |
+
return ""
|
| 332 |
+
labels = labels or {}
|
| 333 |
+
title = labels.get(
|
| 334 |
+
"philo_early_modern_title",
|
| 335 |
+
"Marqueurs typographiques imprimé ancien (XVIᵉ-XVIIIᵉ)",
|
| 336 |
+
)
|
| 337 |
+
note = labels.get(
|
| 338 |
+
"philo_early_modern_note",
|
| 339 |
+
"Préservation des ligatures (fi fl ff), s long (ſ), i sans "
|
| 340 |
+
"point (ı), esperluette (&) et tildes nasaux (ã õ ñ). "
|
| 341 |
+
"Une ligne par moteur, une colonne par catégorie.",
|
| 342 |
+
)
|
| 343 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 344 |
+
global_label = labels.get("philo_global_label", "Global")
|
| 345 |
+
|
| 346 |
+
all_cats: set[str] = set()
|
| 347 |
+
for eng in relevant:
|
| 348 |
+
all_cats.update(
|
| 349 |
+
eng["aggregated_philological"]["early_modern"]
|
| 350 |
+
.get("per_category", {}).keys(),
|
| 351 |
+
)
|
| 352 |
+
cats = sorted(all_cats)
|
| 353 |
+
if not cats:
|
| 354 |
+
return ""
|
| 355 |
+
|
| 356 |
+
parts = [_section_open(title, note), _table_open()]
|
| 357 |
+
parts.append(_table_header([global_label] + cats, engine_label))
|
| 358 |
+
parts.append("<tbody>")
|
| 359 |
+
for eng in relevant:
|
| 360 |
+
agg = eng["aggregated_philological"]["early_modern"]
|
| 361 |
+
n_total = agg.get("n_markers_reference", 0)
|
| 362 |
+
parts.append("<tr>")
|
| 363 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 364 |
+
parts.append(_score_cell(
|
| 365 |
+
agg.get("global_preservation", 0.0), extra=f"n={n_total}",
|
| 366 |
+
))
|
| 367 |
+
per_cat = agg.get("per_category", {})
|
| 368 |
+
for cat in cats:
|
| 369 |
+
stats = per_cat.get(cat)
|
| 370 |
+
if stats and stats.get("total", 0) > 0:
|
| 371 |
+
parts.append(_score_cell(
|
| 372 |
+
stats["preservation"], extra=f"n={stats['total']}",
|
| 373 |
+
))
|
| 374 |
+
else:
|
| 375 |
+
parts.append(_score_cell(None))
|
| 376 |
+
parts.append("</tr>")
|
| 377 |
+
parts.append("</tbody>")
|
| 378 |
+
parts.append(_table_close())
|
| 379 |
+
parts.append(_section_close())
|
| 380 |
+
return "".join(parts)
|
| 381 |
+
|
| 382 |
+
|
| 383 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 384 |
+
# Sprint 59 — Archives modernes : strict + expansion par catégorie
|
| 385 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 386 |
+
|
| 387 |
+
|
| 388 |
+
def build_modern_archives_section(
|
| 389 |
+
engines_summary: list[dict],
|
| 390 |
+
labels: Optional[dict[str, str]] = None,
|
| 391 |
+
) -> str:
|
| 392 |
+
relevant = _engines_with_module(engines_summary, "modern_archives")
|
| 393 |
+
if not relevant:
|
| 394 |
+
return ""
|
| 395 |
+
labels = labels or {}
|
| 396 |
+
title = labels.get(
|
| 397 |
+
"philo_modern_archives_title",
|
| 398 |
+
"Abréviations des archives modernes (XIXᵉ-XXᵉ)",
|
| 399 |
+
)
|
| 400 |
+
note = labels.get(
|
| 401 |
+
"philo_modern_archives_note",
|
| 402 |
+
"Strict = abrégé préservé (Mme, S.A.R., bd, vol., …) ; "
|
| 403 |
+
"Expansion = abrégé OU forme développée. Affiché par "
|
| 404 |
+
"catégorie : civilité, ordinaux, monnaie, administratif, "
|
| 405 |
+
"état civil, ponctuation typo, latin, biblio, adresse.",
|
| 406 |
+
)
|
| 407 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 408 |
+
global_label = labels.get("philo_global_label", "Global")
|
| 409 |
+
strict_label = labels.get("philo_strict_label", "Strict")
|
| 410 |
+
expansion_label = labels.get("philo_expansion_label", "Expansion")
|
| 411 |
+
|
| 412 |
+
all_cats: set[str] = set()
|
| 413 |
+
for eng in relevant:
|
| 414 |
+
all_cats.update(
|
| 415 |
+
eng["aggregated_philological"]["modern_archives"]
|
| 416 |
+
.get("per_category", {}).keys(),
|
| 417 |
+
)
|
| 418 |
+
cats = sorted(all_cats)
|
| 419 |
+
|
| 420 |
+
parts = [_section_open(title, note)]
|
| 421 |
+
parts.append(
|
| 422 |
+
'<table style="border-collapse:collapse;width:100%;'
|
| 423 |
+
'font-size:.85rem">'
|
| 424 |
+
)
|
| 425 |
+
parts.append("<thead><tr>")
|
| 426 |
+
parts.append(
|
| 427 |
+
f'<th rowspan="2" style="padding:.3rem .5rem;text-align:left;'
|
| 428 |
+
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 429 |
+
f'{_e(engine_label)}</th>'
|
| 430 |
+
)
|
| 431 |
+
parts.append(
|
| 432 |
+
f'<th colspan="2" style="padding:.3rem .5rem;text-align:center;'
|
| 433 |
+
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 434 |
+
f'{_e(global_label)}</th>'
|
| 435 |
+
)
|
| 436 |
+
for cat in cats:
|
| 437 |
+
parts.append(
|
| 438 |
+
f'<th colspan="2" style="padding:.3rem .5rem;text-align:center;'
|
| 439 |
+
f'border-bottom:1px solid var(--border);font-weight:600">'
|
| 440 |
+
f'{_e(cat)}</th>'
|
| 441 |
+
)
|
| 442 |
+
parts.append("</tr><tr>")
|
| 443 |
+
for _ in range(1 + len(cats)):
|
| 444 |
+
parts.append(
|
| 445 |
+
f'<th style="padding:.2rem .4rem;text-align:center;'
|
| 446 |
+
f'font-size:.75rem;font-weight:500;opacity:.7">'
|
| 447 |
+
f'{_e(strict_label)}</th>'
|
| 448 |
+
)
|
| 449 |
+
parts.append(
|
| 450 |
+
f'<th style="padding:.2rem .4rem;text-align:center;'
|
| 451 |
+
f'font-size:.75rem;font-weight:500;opacity:.7">'
|
| 452 |
+
f'{_e(expansion_label)}</th>'
|
| 453 |
+
)
|
| 454 |
+
parts.append("</tr></thead>")
|
| 455 |
+
parts.append("<tbody>")
|
| 456 |
+
for eng in relevant:
|
| 457 |
+
agg = eng["aggregated_philological"]["modern_archives"]
|
| 458 |
+
parts.append("<tr>")
|
| 459 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 460 |
+
parts.append(_score_cell(agg.get("global_strict_score", 0.0)))
|
| 461 |
+
parts.append(_score_cell(agg.get("global_expansion_score", 0.0)))
|
| 462 |
+
per_cat = agg.get("per_category", {})
|
| 463 |
+
for cat in cats:
|
| 464 |
+
stats = per_cat.get(cat)
|
| 465 |
+
if stats and stats.get("n_total", 0) > 0:
|
| 466 |
+
parts.append(_score_cell(
|
| 467 |
+
stats["strict_score"],
|
| 468 |
+
extra=f"n={stats['n_total']}",
|
| 469 |
+
))
|
| 470 |
+
parts.append(_score_cell(stats["expansion_score"]))
|
| 471 |
+
else:
|
| 472 |
+
parts.append(_score_cell(None))
|
| 473 |
+
parts.append(_score_cell(None))
|
| 474 |
+
parts.append("</tr>")
|
| 475 |
+
parts.append("</tbody>")
|
| 476 |
+
parts.append(_table_close())
|
| 477 |
+
parts.append(_section_close())
|
| 478 |
+
return "".join(parts)
|
| 479 |
+
|
| 480 |
+
|
| 481 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 482 |
+
# Sprint 60 — Numéraux romains : breakdown 5 statuts
|
| 483 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 484 |
+
|
| 485 |
+
|
| 486 |
+
def build_roman_numerals_section(
|
| 487 |
+
engines_summary: list[dict],
|
| 488 |
+
labels: Optional[dict[str, str]] = None,
|
| 489 |
+
) -> str:
|
| 490 |
+
relevant = _engines_with_module(engines_summary, "roman_numerals")
|
| 491 |
+
if not relevant:
|
| 492 |
+
return ""
|
| 493 |
+
labels = labels or {}
|
| 494 |
+
title = labels.get(
|
| 495 |
+
"philo_roman_numerals_title",
|
| 496 |
+
"Numéraux romains : restitution par statut",
|
| 497 |
+
)
|
| 498 |
+
note = labels.get(
|
| 499 |
+
"philo_roman_numerals_note",
|
| 500 |
+
"Pour chaque numéral romain de la GT, statut de restitution : "
|
| 501 |
+
"strict (forme exacte), case_changed (casse modifiée), "
|
| 502 |
+
"j_dropped (j médiéval normalisé), converted_to_arabic, lost. "
|
| 503 |
+
"Le breakdown indique la convention : majoritaire strict → "
|
| 504 |
+
"diplomatique ; majoritaire arabic → modernisation profonde.",
|
| 505 |
+
)
|
| 506 |
+
engine_label = labels.get("philo_engine_label", "Moteur")
|
| 507 |
+
n_label = labels.get("philo_n_total_label", "n total")
|
| 508 |
+
|
| 509 |
+
statuses = (
|
| 510 |
+
"strict_preserved", "case_changed", "j_dropped",
|
| 511 |
+
"converted_to_arabic", "lost",
|
| 512 |
+
)
|
| 513 |
+
status_labels = {
|
| 514 |
+
s: labels.get(f"philo_roman_status_{s}", s) for s in statuses
|
| 515 |
+
}
|
| 516 |
+
|
| 517 |
+
parts = [_section_open(title, note), _table_open()]
|
| 518 |
+
parts.append(_table_header(
|
| 519 |
+
[n_label] + [status_labels[s] for s in statuses],
|
| 520 |
+
engine_label,
|
| 521 |
+
))
|
| 522 |
+
parts.append("<tbody>")
|
| 523 |
+
for eng in relevant:
|
| 524 |
+
agg = eng["aggregated_philological"]["roman_numerals"]
|
| 525 |
+
n_total = agg.get("n_numerals_reference", 0)
|
| 526 |
+
per_status = agg.get("per_status", {})
|
| 527 |
+
parts.append("<tr>")
|
| 528 |
+
parts.append(_engine_label_cell(eng["name"]))
|
| 529 |
+
parts.append(
|
| 530 |
+
f'<td style="padding:.3rem .5rem;text-align:center">'
|
| 531 |
+
f'{n_total}</td>'
|
| 532 |
+
)
|
| 533 |
+
for status in statuses:
|
| 534 |
+
count = per_status.get(status, 0)
|
| 535 |
+
if n_total > 0:
|
| 536 |
+
ratio = count / n_total
|
| 537 |
+
# Pour « lost » on inverse la couleur (un haut taux
|
| 538 |
+
# de perte est mauvais). Pour les autres on garde
|
| 539 |
+
# la sémantique « plus c'est haut, plus l'OCR a
|
| 540 |
+
# adopté ce statut ».
|
| 541 |
+
color = (
|
| 542 |
+
_color_for_score(1.0 - ratio) if status == "lost"
|
| 543 |
+
else _color_for_score(ratio)
|
| 544 |
+
)
|
| 545 |
+
parts.append(
|
| 546 |
+
f'<td style="padding:.3rem .5rem;text-align:center;'
|
| 547 |
+
f'background:{color}">{count} '
|
| 548 |
+
f'<span style="opacity:.6;font-size:.85em">'
|
| 549 |
+
f'({ratio * 100:.0f}%)</span></td>'
|
| 550 |
+
)
|
| 551 |
+
else:
|
| 552 |
+
parts.append(_score_cell(None))
|
| 553 |
+
parts.append("</tr>")
|
| 554 |
+
parts.append("</tbody>")
|
| 555 |
+
parts.append(_table_close())
|
| 556 |
+
parts.append(_section_close())
|
| 557 |
+
return "".join(parts)
|
| 558 |
+
|
| 559 |
+
|
| 560 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 561 |
+
# Agrégateur principal
|
| 562 |
+
# ──────────────────────────────────────────────────────────────────────────
|
| 563 |
+
|
| 564 |
+
|
| 565 |
+
def build_philological_profile_html(
|
| 566 |
+
engines_summary: list[dict],
|
| 567 |
+
labels: Optional[dict[str, str]] = None,
|
| 568 |
+
) -> str:
|
| 569 |
+
"""Assemble les six sections en un bloc unique.
|
| 570 |
+
|
| 571 |
+
Retourne ``""`` si aucune section n'a de contenu (c.-à-d.
|
| 572 |
+
aucun moteur n'a de signal philologique sur le corpus).
|
| 573 |
+
"""
|
| 574 |
+
sections = [
|
| 575 |
+
build_unicode_blocks_section(engines_summary, labels),
|
| 576 |
+
build_abbreviations_section(engines_summary, labels),
|
| 577 |
+
build_mufi_section(engines_summary, labels),
|
| 578 |
+
build_early_modern_section(engines_summary, labels),
|
| 579 |
+
build_modern_archives_section(engines_summary, labels),
|
| 580 |
+
build_roman_numerals_section(engines_summary, labels),
|
| 581 |
+
]
|
| 582 |
+
non_empty = [s for s in sections if s]
|
| 583 |
+
if not non_empty:
|
| 584 |
+
return ""
|
| 585 |
+
labels = labels or {}
|
| 586 |
+
main_title = labels.get(
|
| 587 |
+
"philo_profile_title", "Profil philologique",
|
| 588 |
+
)
|
| 589 |
+
main_note = labels.get(
|
| 590 |
+
"philo_profile_note",
|
| 591 |
+
"Données brutes par catégorie de marqueur philologique. "
|
| 592 |
+
"L'outil ne classifie pas la convention adoptée par chaque "
|
| 593 |
+
"moteur — c'est au chercheur de lire les chiffres et de "
|
| 594 |
+
"conclure selon ses critères éditoriaux.",
|
| 595 |
+
)
|
| 596 |
+
parts = [
|
| 597 |
+
'<div class="philological-profile">',
|
| 598 |
+
f'<h3 style="margin-top:0">{_e(main_title)}</h3>',
|
| 599 |
+
f'<p style="font-size:.85rem;opacity:.8;margin-bottom:.5rem">'
|
| 600 |
+
f'{_e(main_note)}</p>',
|
| 601 |
+
]
|
| 602 |
+
parts.extend(non_empty)
|
| 603 |
+
parts.append("</div>")
|
| 604 |
+
return "".join(parts)
|
| 605 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 606 |
|
| 607 |
__all__ = [
|
| 608 |
+
"build_philological_profile_html",
|
| 609 |
+
"build_unicode_blocks_section",
|
| 610 |
+
"build_abbreviations_section",
|
| 611 |
+
"build_mufi_section",
|
| 612 |
+
"build_early_modern_section",
|
| 613 |
+
"build_modern_archives_section",
|
| 614 |
+
"build_roman_numerals_section",
|
| 615 |
]
|
picarones/report/taxonomy_cooccurrence_render.py
CHANGED
|
@@ -1,26 +1,199 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
aux imports historiques (y compris les noms privés ``_*``) de
|
| 5 |
-
continuer à fonctionner sans modification.
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
-
# Réexport explicite de TOUS les noms (privés inclus) pour la
|
| 13 |
-
# rétrocompatibilité des tests Sprints qui importent ``_helper``,
|
| 14 |
-
# ``_compute_X``, ``_SCIPY_AVAILABLE``, etc. Sans cette boucle, ``import *``
|
| 15 |
-
# ne propage que les noms publics et casse les imports historiques.
|
| 16 |
-
import picarones.extras.render.taxonomy_cooccurrence_render as _shim_module
|
| 17 |
-
for _shim_name in dir(_shim_module):
|
| 18 |
-
if _shim_name == "__builtins__":
|
| 19 |
-
continue
|
| 20 |
-
if _shim_name not in globals():
|
| 21 |
-
globals()[_shim_name] = getattr(_shim_module, _shim_name)
|
| 22 |
-
del _shim_module, _shim_name
|
| 23 |
|
| 24 |
__all__ = [
|
| 25 |
-
|
| 26 |
]
|
|
|
|
| 1 |
+
"""Rendu HTML de la heatmap de co-occurrence taxonomique — Sprint 75.
|
| 2 |
|
| 3 |
+
A.I.4 chantier 1 du plan d'évolution 2026.
|
|
|
|
|
|
|
| 4 |
|
| 5 |
+
Suite directe ``picarones/core/taxonomy_cooccurrence.py``. Pattern
|
| 6 |
+
identique aux autres rendus (Sprints 41/43/62/67/72/74) :
|
| 7 |
+
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
+
|
| 9 |
+
Sortie typique
|
| 10 |
+
--------------
|
| 11 |
+
- ``build_taxonomy_cooccurrence_html(data, labels)`` produit un
|
| 12 |
+
bloc complet : titre + note d'usage + heatmap SVG + table des
|
| 13 |
+
paires les plus co-occurrentes.
|
| 14 |
+
- ``""`` retourné si ``data is None`` ou si la matrice est vide
|
| 15 |
+
(rapport adaptatif).
|
| 16 |
"""
|
| 17 |
|
| 18 |
+
from __future__ import annotations
|
| 19 |
+
|
| 20 |
+
from html import escape as _e
|
| 21 |
+
from typing import Optional
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
def _color_for_jaccard(j: float) -> str:
|
| 25 |
+
"""Gradient blanc → bleu profond pour Jaccard ∈ [0, 1].
|
| 26 |
+
|
| 27 |
+
Interpolation entre #ffffff (j=0) et #1e3a8a (j=1).
|
| 28 |
+
"""
|
| 29 |
+
f = max(0.0, min(1.0, j))
|
| 30 |
+
r = int(255 + (30 - 255) * f)
|
| 31 |
+
g = int(255 + (58 - 255) * f)
|
| 32 |
+
b = int(255 + (138 - 255) * f)
|
| 33 |
+
return f"#{r:02x}{g:02x}{b:02x}"
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
def _text_color_for_bg(j: float) -> str:
|
| 37 |
+
"""Texte blanc si fond foncé, noir sinon (lisibilité)."""
|
| 38 |
+
return "#fff" if j > 0.55 else "#222"
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
def _build_heatmap_svg(
|
| 42 |
+
classes: list[str],
|
| 43 |
+
matrix: dict[str, dict[str, float]],
|
| 44 |
+
*,
|
| 45 |
+
cell_size: int = 36,
|
| 46 |
+
label_left: int = 130,
|
| 47 |
+
label_top: int = 80,
|
| 48 |
+
) -> str:
|
| 49 |
+
"""Construit la heatmap SVG.
|
| 50 |
+
|
| 51 |
+
Cellule = carré coloré ``_color_for_jaccard``, valeur Jaccard
|
| 52 |
+
affichée en chiffres si > 0,05. Étiquettes des classes en
|
| 53 |
+
colonne (haut) et en ligne (gauche).
|
| 54 |
+
"""
|
| 55 |
+
n = len(classes)
|
| 56 |
+
if n == 0:
|
| 57 |
+
return ""
|
| 58 |
+
width = label_left + n * cell_size + 10
|
| 59 |
+
height = label_top + n * cell_size + 10
|
| 60 |
+
|
| 61 |
+
parts = [
|
| 62 |
+
f'<svg xmlns="http://www.w3.org/2000/svg" '
|
| 63 |
+
f'width="{width}" height="{height}" '
|
| 64 |
+
f'viewBox="0 0 {width} {height}" '
|
| 65 |
+
f'role="img" aria-label="Heatmap Jaccard co-occurrence taxonomique">',
|
| 66 |
+
]
|
| 67 |
+
# Étiquettes de colonnes (rotées -45°)
|
| 68 |
+
for j, cls in enumerate(classes):
|
| 69 |
+
cx = label_left + j * cell_size + cell_size // 2
|
| 70 |
+
cy = label_top - 6
|
| 71 |
+
parts.append(
|
| 72 |
+
f'<text x="{cx}" y="{cy}" '
|
| 73 |
+
f'transform="rotate(-45 {cx} {cy})" '
|
| 74 |
+
f'font-size="11" fill="#333" text-anchor="start">'
|
| 75 |
+
f'{_e(cls)}</text>'
|
| 76 |
+
)
|
| 77 |
+
# Étiquettes de lignes
|
| 78 |
+
for i, cls in enumerate(classes):
|
| 79 |
+
rx = label_left - 6
|
| 80 |
+
ry = label_top + i * cell_size + cell_size // 2 + 4
|
| 81 |
+
parts.append(
|
| 82 |
+
f'<text x="{rx}" y="{ry}" '
|
| 83 |
+
f'font-size="11" fill="#333" text-anchor="end">'
|
| 84 |
+
f'{_e(cls)}</text>'
|
| 85 |
+
)
|
| 86 |
+
# Cellules
|
| 87 |
+
for i, ca in enumerate(classes):
|
| 88 |
+
for j, cb in enumerate(classes):
|
| 89 |
+
value = matrix.get(ca, {}).get(cb, 0.0)
|
| 90 |
+
x = label_left + j * cell_size
|
| 91 |
+
y = label_top + i * cell_size
|
| 92 |
+
color = _color_for_jaccard(value)
|
| 93 |
+
text_color = _text_color_for_bg(value)
|
| 94 |
+
parts.append(
|
| 95 |
+
f'<rect x="{x}" y="{y}" '
|
| 96 |
+
f'width="{cell_size}" height="{cell_size}" '
|
| 97 |
+
f'fill="{color}" stroke="#ddd" stroke-width="0.5"/>'
|
| 98 |
+
)
|
| 99 |
+
if value > 0.05:
|
| 100 |
+
parts.append(
|
| 101 |
+
f'<text x="{x + cell_size // 2}" '
|
| 102 |
+
f'y="{y + cell_size // 2 + 4}" '
|
| 103 |
+
f'font-size="10" fill="{text_color}" '
|
| 104 |
+
f'text-anchor="middle">'
|
| 105 |
+
f'{value:.2f}</text>'
|
| 106 |
+
)
|
| 107 |
+
parts.append("</svg>")
|
| 108 |
+
return "".join(parts)
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
def _build_top_pairs_table(
|
| 112 |
+
top_pairs: list,
|
| 113 |
+
labels: dict,
|
| 114 |
+
) -> str:
|
| 115 |
+
"""Construit la table HTML des paires les plus co-occurrentes."""
|
| 116 |
+
if not top_pairs:
|
| 117 |
+
return ""
|
| 118 |
+
pair_label = labels.get("taxocooc_pair_label", "Paire")
|
| 119 |
+
jaccard_label = labels.get("taxocooc_jaccard_label", "Jaccard")
|
| 120 |
+
|
| 121 |
+
parts = [
|
| 122 |
+
'<table style="border-collapse:collapse;font-size:.85rem;'
|
| 123 |
+
'margin-top:.5rem">',
|
| 124 |
+
'<thead><tr>',
|
| 125 |
+
f'<th style="padding:.3rem .5rem;text-align:left;'
|
| 126 |
+
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 127 |
+
f'{_e(pair_label)}</th>',
|
| 128 |
+
f'<th style="padding:.3rem .5rem;text-align:right;'
|
| 129 |
+
f'border-bottom:1px solid #ccc;font-weight:600">'
|
| 130 |
+
f'{_e(jaccard_label)}</th>',
|
| 131 |
+
'</tr></thead><tbody>',
|
| 132 |
+
]
|
| 133 |
+
for ca, cb, j in top_pairs:
|
| 134 |
+
parts.append(
|
| 135 |
+
f'<tr>'
|
| 136 |
+
f'<td style="padding:.2rem .5rem">'
|
| 137 |
+
f'<code>{_e(ca)}</code> ↔ <code>{_e(cb)}</code></td>'
|
| 138 |
+
f'<td style="padding:.2rem .5rem;text-align:right;'
|
| 139 |
+
f'font-family:monospace;background:{_color_for_jaccard(j)};'
|
| 140 |
+
f'color:{_text_color_for_bg(j)}">{j:.2f}</td>'
|
| 141 |
+
f'</tr>'
|
| 142 |
+
)
|
| 143 |
+
parts.append("</tbody></table>")
|
| 144 |
+
return "".join(parts)
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
def build_taxonomy_cooccurrence_html(
|
| 148 |
+
data: Optional[dict],
|
| 149 |
+
labels: Optional[dict[str, str]] = None,
|
| 150 |
+
) -> str:
|
| 151 |
+
"""Construit le bloc HTML complet de co-occurrence taxonomique.
|
| 152 |
+
|
| 153 |
+
Retourne ``""`` si ``data is None`` ou matrice vide.
|
| 154 |
+
"""
|
| 155 |
+
if not data:
|
| 156 |
+
return ""
|
| 157 |
+
classes = data.get("classes") or []
|
| 158 |
+
matrix = data.get("cooccurrence_matrix") or {}
|
| 159 |
+
if not classes or not matrix:
|
| 160 |
+
return ""
|
| 161 |
+
labels = labels or {}
|
| 162 |
+
title = labels.get(
|
| 163 |
+
"taxocooc_title",
|
| 164 |
+
"Co-occurrence des classes d'erreur",
|
| 165 |
+
)
|
| 166 |
+
note = labels.get(
|
| 167 |
+
"taxocooc_note",
|
| 168 |
+
"Indice de Jaccard au niveau document : 1,00 = ces deux classes "
|
| 169 |
+
"apparaissent toujours ensemble ; 0,00 = jamais. Lecture par paires "
|
| 170 |
+
"co-occurrentes ci-dessous.",
|
| 171 |
+
)
|
| 172 |
+
n_docs = data.get("n_documents", 0)
|
| 173 |
+
n_docs_label_template = labels.get(
|
| 174 |
+
"taxocooc_n_docs", "Calculé sur {n_docs} documents.",
|
| 175 |
+
)
|
| 176 |
+
n_docs_phrase = n_docs_label_template.format(n_docs=n_docs)
|
| 177 |
+
|
| 178 |
+
svg = _build_heatmap_svg(classes, matrix)
|
| 179 |
+
top_table = _build_top_pairs_table(
|
| 180 |
+
data.get("top_pairs") or [], labels,
|
| 181 |
+
)
|
| 182 |
+
|
| 183 |
+
parts = [
|
| 184 |
+
'<div class="taxocooc" style="margin:1rem 0">',
|
| 185 |
+
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 186 |
+
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 187 |
+
f'{_e(note)}</div>',
|
| 188 |
+
f'<div style="font-size:.8rem;opacity:.7;margin-bottom:.5rem">'
|
| 189 |
+
f'{_e(n_docs_phrase)}</div>',
|
| 190 |
+
svg,
|
| 191 |
+
top_table,
|
| 192 |
+
"</div>",
|
| 193 |
+
]
|
| 194 |
+
return "".join(parts)
|
| 195 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 196 |
|
| 197 |
__all__ = [
|
| 198 |
+
"build_taxonomy_cooccurrence_html",
|
| 199 |
]
|
picarones/report/taxonomy_intra_doc_render.py
CHANGED
|
@@ -1,26 +1,182 @@
|
|
| 1 |
-
"""
|
| 2 |
|
| 3 |
-
|
| 4 |
-
aux imports historiques (y compris les noms privés ``_*``) de
|
| 5 |
-
continuer à fonctionner sans modification.
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"""
|
| 9 |
|
| 10 |
-
from
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
-
# Réexport explicite de TOUS les noms (privés inclus) pour la
|
| 13 |
-
# rétrocompatibilité des tests Sprints qui importent ``_helper``,
|
| 14 |
-
# ``_compute_X``, ``_SCIPY_AVAILABLE``, etc. Sans cette boucle, ``import *``
|
| 15 |
-
# ne propage que les noms publics et casse les imports historiques.
|
| 16 |
-
import picarones.extras.render.taxonomy_intra_doc_render as _shim_module
|
| 17 |
-
for _shim_name in dir(_shim_module):
|
| 18 |
-
if _shim_name == "__builtins__":
|
| 19 |
-
continue
|
| 20 |
-
if _shim_name not in globals():
|
| 21 |
-
globals()[_shim_name] = getattr(_shim_module, _shim_name)
|
| 22 |
-
del _shim_module, _shim_name
|
| 23 |
|
| 24 |
__all__ = [
|
| 25 |
-
|
| 26 |
]
|
|
|
|
| 1 |
+
"""Rendu HTML de la heatmap class × position — Sprint 76.
|
| 2 |
|
| 3 |
+
A.I.4 chantier 2 du plan d'évolution 2026.
|
|
|
|
|
|
|
| 4 |
|
| 5 |
+
Suite directe ``picarones/core/taxonomy_intra_doc.py``. Pattern
|
| 6 |
+
identique aux autres rendus (Sprints 41/43/62/67/72/74/75) :
|
| 7 |
+
**server-side**, pas de JavaScript, anti-injection systématique.
|
| 8 |
+
|
| 9 |
+
Sortie typique
|
| 10 |
+
--------------
|
| 11 |
+
Une grille N_classes × N_bins où chaque cellule indique la densité
|
| 12 |
+
d'erreurs de cette classe à cette position dans le document.
|
| 13 |
+
Lecture immédiate : « ligature_error concentré dans la première
|
| 14 |
+
tranche → erreur de marge ; visual_confusion uniformément réparti
|
| 15 |
+
→ erreur de scribe ».
|
| 16 |
+
|
| 17 |
+
Adaptive : si ``data is None`` ou si toutes les classes ont 0
|
| 18 |
+
erreur, retourne ``""``.
|
| 19 |
"""
|
| 20 |
|
| 21 |
+
from __future__ import annotations
|
| 22 |
+
|
| 23 |
+
from html import escape as _e
|
| 24 |
+
from typing import Optional
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
def _color_for_density(density: float) -> str:
|
| 28 |
+
"""Gradient blanc → orange profond pour densité ∈ [0, 1].
|
| 29 |
+
|
| 30 |
+
Interpolation entre #ffffff (0) et #c2410c (1).
|
| 31 |
+
"""
|
| 32 |
+
f = max(0.0, min(1.0, density))
|
| 33 |
+
r = int(255 + (194 - 255) * f)
|
| 34 |
+
g = int(255 + (65 - 255) * f)
|
| 35 |
+
b = int(255 + (12 - 255) * f)
|
| 36 |
+
return f"#{r:02x}{g:02x}{b:02x}"
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
def _text_color_for_bg(density: float) -> str:
|
| 40 |
+
return "#fff" if density > 0.55 else "#222"
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
def _build_heatmap_svg(
|
| 44 |
+
classes_with_errors: list[str],
|
| 45 |
+
per_class: dict[str, list[int]],
|
| 46 |
+
n_bins: int,
|
| 47 |
+
*,
|
| 48 |
+
cell_w: int = 36,
|
| 49 |
+
cell_h: int = 26,
|
| 50 |
+
label_left: int = 150,
|
| 51 |
+
label_top: int = 30,
|
| 52 |
+
) -> str:
|
| 53 |
+
"""Construit la heatmap SVG class × position."""
|
| 54 |
+
n_rows = len(classes_with_errors)
|
| 55 |
+
if n_rows == 0:
|
| 56 |
+
return ""
|
| 57 |
+
width = label_left + n_bins * cell_w + 10
|
| 58 |
+
height = label_top + n_rows * cell_h + 30 # +30 pour étiquette X
|
| 59 |
+
|
| 60 |
+
# Normalisation : pour chaque classe, densité relative au max
|
| 61 |
+
# de cette classe (mise en évidence des positions concentrées).
|
| 62 |
+
parts = [
|
| 63 |
+
f'<svg xmlns="http://www.w3.org/2000/svg" '
|
| 64 |
+
f'width="{width}" height="{height}" '
|
| 65 |
+
f'viewBox="0 0 {width} {height}" '
|
| 66 |
+
f'role="img" aria-label="Heatmap class taxonomique × position">',
|
| 67 |
+
]
|
| 68 |
+
# Étiquettes des colonnes (positions)
|
| 69 |
+
for j in range(n_bins):
|
| 70 |
+
cx = label_left + j * cell_w + cell_w // 2
|
| 71 |
+
cy = label_top - 6
|
| 72 |
+
parts.append(
|
| 73 |
+
f'<text x="{cx}" y="{cy}" '
|
| 74 |
+
f'font-size="10" fill="#666" text-anchor="middle">'
|
| 75 |
+
f'{j + 1}</text>'
|
| 76 |
+
)
|
| 77 |
+
# Cellules
|
| 78 |
+
for i, cls in enumerate(classes_with_errors):
|
| 79 |
+
# Étiquette de ligne (classe)
|
| 80 |
+
rx = label_left - 6
|
| 81 |
+
ry = label_top + i * cell_h + cell_h // 2 + 4
|
| 82 |
+
parts.append(
|
| 83 |
+
f'<text x="{rx}" y="{ry}" '
|
| 84 |
+
f'font-size="11" fill="#333" text-anchor="end">'
|
| 85 |
+
f'{_e(cls)}</text>'
|
| 86 |
+
)
|
| 87 |
+
counts = per_class.get(cls, [0] * n_bins)
|
| 88 |
+
max_count = max(counts) if counts else 0
|
| 89 |
+
for j in range(n_bins):
|
| 90 |
+
x = label_left + j * cell_w
|
| 91 |
+
y = label_top + i * cell_h
|
| 92 |
+
count = counts[j] if j < len(counts) else 0
|
| 93 |
+
density = (count / max_count) if max_count > 0 else 0.0
|
| 94 |
+
color = _color_for_density(density)
|
| 95 |
+
text_color = _text_color_for_bg(density)
|
| 96 |
+
parts.append(
|
| 97 |
+
f'<rect x="{x}" y="{y}" '
|
| 98 |
+
f'width="{cell_w}" height="{cell_h}" '
|
| 99 |
+
f'fill="{color}" stroke="#ddd" stroke-width="0.5"/>'
|
| 100 |
+
)
|
| 101 |
+
if count > 0:
|
| 102 |
+
parts.append(
|
| 103 |
+
f'<text x="{x + cell_w // 2}" '
|
| 104 |
+
f'y="{y + cell_h // 2 + 4}" '
|
| 105 |
+
f'font-size="10" fill="{text_color}" '
|
| 106 |
+
f'text-anchor="middle">{count}</text>'
|
| 107 |
+
)
|
| 108 |
+
# Étiquette axe X en bas
|
| 109 |
+
cx_axis = label_left + (n_bins * cell_w) // 2
|
| 110 |
+
cy_axis = height - 6
|
| 111 |
+
parts.append(
|
| 112 |
+
f'<text x="{cx_axis}" y="{cy_axis}" '
|
| 113 |
+
f'font-size="11" fill="#666" text-anchor="middle" '
|
| 114 |
+
f'font-style="italic">'
|
| 115 |
+
f'Position dans le document (1 = début)</text>'
|
| 116 |
+
)
|
| 117 |
+
parts.append("</svg>")
|
| 118 |
+
return "".join(parts)
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
def build_taxonomy_intra_doc_html(
|
| 122 |
+
data: Optional[dict],
|
| 123 |
+
labels: Optional[dict[str, str]] = None,
|
| 124 |
+
) -> str:
|
| 125 |
+
"""Construit le bloc HTML complet de la heatmap intra-document.
|
| 126 |
+
|
| 127 |
+
Retourne ``""`` si ``data is None`` ou aucune erreur.
|
| 128 |
+
"""
|
| 129 |
+
if not data:
|
| 130 |
+
return ""
|
| 131 |
+
n_bins = data.get("n_bins", 0)
|
| 132 |
+
per_class = data.get("per_class") or {}
|
| 133 |
+
total_errors = data.get("total_errors", 0)
|
| 134 |
+
if total_errors == 0 or n_bins <= 0:
|
| 135 |
+
return ""
|
| 136 |
+
# Filtre : uniquement les classes ayant au moins une erreur
|
| 137 |
+
classes_with_errors = [
|
| 138 |
+
cls for cls, counts in per_class.items()
|
| 139 |
+
if isinstance(counts, list) and sum(counts) > 0
|
| 140 |
+
]
|
| 141 |
+
if not classes_with_errors:
|
| 142 |
+
return ""
|
| 143 |
+
|
| 144 |
+
labels = labels or {}
|
| 145 |
+
title = labels.get(
|
| 146 |
+
"intradoc_title",
|
| 147 |
+
"Évolution intra-document des classes d'erreur",
|
| 148 |
+
)
|
| 149 |
+
note = labels.get(
|
| 150 |
+
"intradoc_note",
|
| 151 |
+
"Heatmap class × position : densité relative par classe "
|
| 152 |
+
"(plus foncé = concentré). Une classe concentrée dans la "
|
| 153 |
+
"première colonne suggère une erreur de marge ; "
|
| 154 |
+
"une distribution uniforme suggère une erreur de scribe.",
|
| 155 |
+
)
|
| 156 |
+
n_words_gt = data.get("n_words_gt", 0)
|
| 157 |
+
n_words_template = labels.get(
|
| 158 |
+
"intradoc_n_words",
|
| 159 |
+
"Calculé sur {n_words_gt} mots GT, répartis en {n_bins} tranches.",
|
| 160 |
+
)
|
| 161 |
+
n_words_phrase = n_words_template.format(
|
| 162 |
+
n_words_gt=n_words_gt, n_bins=n_bins,
|
| 163 |
+
)
|
| 164 |
+
|
| 165 |
+
svg = _build_heatmap_svg(classes_with_errors, per_class, n_bins)
|
| 166 |
+
|
| 167 |
+
parts = [
|
| 168 |
+
'<div class="intradoc" style="margin:1rem 0">',
|
| 169 |
+
f'<div style="font-weight:600;margin-bottom:.4rem">{_e(title)}</div>',
|
| 170 |
+
f'<div style="font-size:.85rem;opacity:.75;margin-bottom:.5rem">'
|
| 171 |
+
f'{_e(note)}</div>',
|
| 172 |
+
f'<div style="font-size:.8rem;opacity:.7;margin-bottom:.5rem">'
|
| 173 |
+
f'{_e(n_words_phrase)}</div>',
|
| 174 |
+
svg,
|
| 175 |
+
"</div>",
|
| 176 |
+
]
|
| 177 |
+
return "".join(parts)
|
| 178 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
|
| 180 |
__all__ = [
|
| 181 |
+
"build_taxonomy_intra_doc_html",
|
| 182 |
]
|