colin/colibre
1
0
Fork 0
Code Issues 30 Pull Requests Actions Packages Projects Releases 33 Activity

Merge branch 'feature/58_search' into dev

Browse Source
This commit is contained in:
Colin Maudry
2025-11-12 14:56:37 +01:00
parent 1310caef4d bb6c0dec26
commit a3f8bd0981
6 changed files with 270 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -1
View File
@@ -40,8 +40,9 @@ Ne pas oublier de mettre à jour les fichier .env.
#### 2.2.0 ()
- Moteur de recherche (acheteurs et titulaires) en page d'accueil ([#58](https://github.com/ColinMaudry/decp.info/issues/58))
- Top acheteurs / titulaires par montant attribué/remporté (([#55](https://github.com/ColinMaudry/decp.info/issues/55)))
- Moins de colonnes affichées par défaut ([#54](https://github.com/ColinMaudry/decp.info/issues/54))
- Moins de colonnes affichées par défaut dans Tableau ([#54](https://github.com/ColinMaudry/decp.info/issues/54))
##### 2.1.7 (11 novembre 2025)
pyproject.toml
+2 -1
View File
@@ -16,7 +16,8 @@ dependencies = [
"xlsxwriter",
"plotly[express]",
"httpx",
"pandas" # utilisé pour la création de certains graphiques
"pandas", # utilisé pour la création de certains graphiques
"unidecode"
]
[project.optional-dependencies]
src/assets/style.css
+30 -4
View File
@@ -148,6 +148,35 @@ td[data-dash-column="objet"],td[data-dash-column="titulaire_nom"],td[data-dash-c
margin-top: 25px;
}
/* Page de recherche */
#search {
margin: 50px auto 0px auto;
width: 450px;
font-size: 18px;
height: 30px;
display: block;
}
.search_options {
margin: 16px auto;
width: 450px;
}
.search_options input {
margin-right: 12px;
}
.results_acheteur {
grid-column: 1;
grid-row: 1;
}
.results_titulaire {
grid-column: 2;
grid-row: 1;
}
/* Menu de navigation */
.navbar {
@@ -177,7 +206,7 @@ summary > h3 {
padding-top: 28px;
}
/* Vue acheteur/titulaire */
/* Vue acheteur/titulaire/recherche */
.wrapper {
display: grid;
grid-gap: 10px;
@@ -185,9 +214,6 @@ summary > h3 {
justify-content: space-between;
}
.wrapper > div {
}
.org_title {
grid-column: 1 / 3;
grid-row: 1;
src/pages/recherche.py
+104
View File
@@ -0,0 +1,104 @@
from dash import Input, Output, callback, dash_table, dcc, html, register_page
from src.utils import (
df_acheteurs,
df_titulaires,
meta_content,
search_org,
setup_table_columns,
)
name = "Recherche"
register_page(
__name__,
path="/",
title=meta_content["title"],
name=name,
description=meta_content["description"],
image_url=meta_content["image_url"],
order=0,
)
layout = html.Div(
className="container",
children=[
dcc.Input(
id="search",
type="text",
placeholder="Nom d'acheteur, d'entreprise, SIREN...",
),
# html.Div(
# className="search_options",
# children=[dcc.RadioItems(options=["Acheteur(s)"])],
# ),
html.Div(id="search_results", className="wrapper"),
],
)
@callback(
Output("search_results", "children"),
Input("search", "value"),
prevent_initial_call=True,
)
def update_search_results(query):
if len(query) >= 1:
content = []
for org_type in ["acheteur", "titulaire"]:
if org_type == "acheteur":
dff = df_acheteurs
elif org_type == "titulaire":
dff = df_titulaires
else:
raise ValueError(f"{org_type} is not supported")
# Search acheteurs and titulaires using the same function
results = search_org(dff, query, org_type=org_type)
count = results.height
# Format output
columns, tooltip = setup_table_columns(results, hideable=False)
org_content = [
html.Div(
className=f"results_{org_type}",
children=[
html.H3(f"{org_type.title()}s : {count}"),
dash_table.DataTable(
columns=columns,
data=results.to_dicts(),
page_size=10,
# style_table={"overflowX": "auto"},
markdown_options={"html": True},
cell_selectable=False,
style_cell_conditional=[
{
"if": {"column_id": "acheteur_nom"},
"maxWidth": "250px",
"textAlign": "left",
"overflow": "hidden",
"lineHeight": "18px",
"whiteSpace": "normal",
},
{
"if": {"column_id": "titulaire_nom"},
"maxWidth": "250px",
"textAlign": "left",
"overflow": "hidden",
"lineHeight": "18px",
"whiteSpace": "normal",
},
],
),
],
)
if count > 0
else html.P(f"Aucun {org_type} trouvé."),
]
content.extend(org_content)
return content
else:
return html.P("")
src/pages/tableau.py
+1 -1
View File
@@ -25,7 +25,7 @@ schema = df.collect_schema()
name = "Tableau"
register_page(
__name__,
path="/",
path="/tableau",
title=meta_content["title"],
name=name,
description=meta_content["description"],
src/utils.py
+120 -13
View File
@@ -8,6 +8,7 @@ import polars.selectors as cs
from httpx import get
from polars import Schema
from polars.exceptions import ComputeError
from unidecode import unidecode
operators = [
["s<", "<"],
@@ -50,29 +51,46 @@ def add_resource_link(dff: pl.DataFrame) -> pl.DataFrame:
return dff
def add_links(dff: pl.DataFrame):
def add_links(dff: pl.DataFrame, target: str = "_blank"):
for col in ["uid", "acheteur_nom", "titulaire_nom", "acheteur_id", "titulaire_id"]:
if col in dff.columns:
if col.startswith("titulaire_"):
dff = dff.with_columns(
pl.when(pl.col("titulaire_typeIdentifiant") == "SIRET")
pl.when(
pl.Expr.or_(
pl.col("titulaire_typeIdentifiant").is_null(),
pl.col("titulaire_typeIdentifiant") == "SIRET",
)
)
.then(
'<a href = "/titulaires/'
+ pl.col("titulaire_id")
+ '">'
+ pl.col("titulaire_id")
+ f'" target="{target}">'
+ pl.col(col)
+ "</a>"
)
.otherwise(pl.col("titulaire_id"))
.alias("titulaire_id")
.otherwise(pl.col(col))
.alias(col)
)
for column, path in [("acheteur_id", "acheteurs"), ("uid", "marches")]:
if col.startswith("acheteur_"):
dff = dff.with_columns(
(
f'<a href = "/{path}/'
+ pl.col(column)
+ '" target="_blank">'
+ pl.col(column)
'<a href = "/acheteurs/'
+ pl.col("acheteur_id")
+ f'" target="{target}">'
+ pl.col(col)
+ "</a>"
).alias(column)
).alias(col)
)
if col == "uid":
dff = dff.with_columns(
(
'<a href = "/marches/'
+ pl.col("uid")
+ f'" target="{target}">'
+ pl.col("uid")
+ "</a>"
).alias("uid")
)
return dff
@@ -208,6 +226,18 @@ def get_decp_data() -> pl.DataFrame:
return lff.collect()
def get_org_data(dff: pl.DataFrame, org_type: str) -> pl.DataFrame:
lff = dff.lazy()
lff = lff.select(
"uid",
cs.starts_with(org_type).exclude(
f"{org_type}_latitude", f"{org_type}_longitude"
),
)
lff = lff.group_by(cs.starts_with(org_type)).len("Marchés")
return lff.collect()
def get_departements() -> dict:
with open("data/departements.json", "rb") as f:
data = json.load(f)
@@ -364,7 +394,84 @@ def get_data_schema() -> dict:
return new_schema
def search_org(dff: pl.DataFrame, query: str, org_type: str) -> pl.DataFrame:
"""
Search in either 'acheteur' or 'titulaire' DataFrame.
:param dff: Polars DataFrame with acheteur or titulaire columns
:param query: User search string
:param org_type: 'acheteur' or 'titulaire'
:return: Filtered DataFrame with 'matches' column
"""
if not query.strip():
return dff.select(pl.lit(False).alias("matches"))
sleep(0.2)
# Normalize query
normalized_query = unidecode(query.strip()).upper()
tokens = [" " + t.strip() for t in normalized_query.split() if t.strip()]
# Define columns based on entity type
cols = [
f"{org_type}_id",
f"{org_type}_nom",
f"{org_type}_departement_nom",
f"{org_type}_departement_code",
f"{org_type}_commune_nom",
]
# Concatenate all fields into one string per row
org_str = pl.concat_str(pl.lit(" "), pl.col(cols), separator=" ")
# For each token, create a boolean column: True if token is found
token_matches = []
for token in tokens:
token_match = org_str.str.contains(token).alias(f"token_{token}")
token_matches.append(token_match)
# Count how many tokens match per row
match_score = pl.sum_horizontal(token_matches).alias("match_score")
# For each token, create a boolean column: True if token is found
token_matches = []
for token in tokens:
token_match = org_str.str.contains(token).alias(f"token_{token}")
token_matches.append(token_match)
# Sélection des colonnes
if org_type == "acheteur":
dff = dff.select(cols + ["Marchés"])
if org_type == "titulaire":
dff = dff.select(cols + ["Marchés", "titulaire_typeIdentifiant"])
# Apply and filter
dff = (
dff.with_columns(token_matches + [match_score])
.filter(pl.col("match_score") == len(tokens))
.sort("Marchés", descending=True)
.drop([f"token_{token}" for token in tokens])
)
# Format result
dff = add_links(dff, target="")
dff = dff.with_columns(
pl.concat_str(
pl.col(f"{org_type}_departement_nom"),
pl.lit(" ("),
pl.col(f"{org_type}_departement_code"),
pl.lit(")"),
).alias("Département")
)
dff = dff.select(f"{org_type}_id", f"{org_type}_nom", "Département", "Marchés")
return dff
df: pl.DataFrame = get_decp_data()
df_acheteurs = get_org_data(df, "acheteur")
df_titulaires = get_org_data(df, "titulaire")
departements = get_departements()
domain_name = (
"test.decp.info" if os.getenv("DEVELOPMENT").lower() == "true" else "decp.info"