From ee686a3207d2e09af873bd2cca3664c974a27da0 Mon Sep 17 00:00:00 2001
From: ulihhhh <54112476+ulihhhh@users.noreply.github.com>
Date: Sat, 17 Oct 2026 01:17:13 +0200
Subject: [PATCH] fix(gbfs): read underscores in station names as word breaks

JCDecaux's Spanish contracts prefix every station name with "_", and
Valenbisi joins its words with it ("_PLAZA_MUSICO_LOPEZ_CHAVARRI"), so
the card and HUD would show the raw identifier. The shared parser now
reads a run of underscores, with the spaces around it, as one word break
and trims the ends. It applies to `name`, the `short_name` fallback and
GBFS v3 localized names, so the layer and get_bike_share both read it.

No registered system changes: run over all 52 live station_information
feeds on 2026-10-17, the old and new parsers give identical names for
all 13,397 stations. Other spacing stays as the operator published it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---
 src/sources/gbfsStations.js       | 14 ++++++++++--
 src/sources/gbfsStations.test.mjs | 36 +++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/src/sources/gbfsStations.js b/src/sources/gbfsStations.js
index 74f2efd23..dd4eff898 100644
--- a/src/sources/gbfsStations.js
+++ b/src/sources/gbfsStations.js
@@ -51,15 +51,25 @@ export function extractStationsArray(payload) {
   return [];
 }
 
+/**
+ * Station name text as a reader expects it. JCDecaux's Spanish contracts
+ * (Valenbisi, Sevici) prefix every name with "_" and Valenbisi joins words
+ * with it ("_PLAZA_MUSICO_LOPEZ_CHAVARRI"), so an underscore reads as a word
+ * break. Other spacing is the operator's own and stays as published.
+ */
+function tidyStationName(text) {
+  return text.replace(/\s*_+\s*/g, ' ').trim();
+}
+
 /** Read legacy text or a GBFS v3 Localized String, preferring usable English text. */
 function stationName(value) {
-  if (typeof value === 'string') return value.trim();
+  if (typeof value === 'string') return tidyStationName(value);
   if (!Array.isArray(value)) return '';
 
   let fallback = '';
   for (const translation of value) {
     if (typeof translation?.text !== 'string') continue;
-    const text = translation.text.trim();
+    const text = tidyStationName(translation.text);
     if (!text) continue;
     if (!fallback) fallback = text;
     if (
diff --git a/src/sources/gbfsStations.test.mjs b/src/sources/gbfsStations.test.mjs
index 8c60da90c..6f12db258 100644
--- a/src/sources/gbfsStations.test.mjs
+++ b/src/sources/gbfsStations.test.mjs
@@ -22,6 +22,42 @@ test('GBFS v2 station names remain trimmed strings', () => {
   );
 });
 
+test('underscores in station names read as word breaks', () => {
+  // As published by JCDecaux's Spanish contracts (checked 2026-10-17).
+  for (const [published, shown] of [
+    ['_PLAZA_MUSICO_LOPEZ_CHAVARRI', 'PLAZA MUSICO LOPEZ CHAVARRI'],
+    ['_GLORIETA OLIMPICA', 'GLORIETA OLIMPICA'],
+    ['_CAMPAMENTO_81', 'CAMPAMENTO 81'],
+    ['Plaza__Mayor_ ', 'Plaza Mayor'],
+  ]) {
+    assert.equal(parseName({ name: published }), shown);
+  }
+});
+
+test('spacing without underscores stays as the operator published it', () => {
+  assert.equal(parseName({ name: 'C/  NÀPOLS, 82' }), 'C/  NÀPOLS, 82');
+});
+
+test('a name of only underscores falls back to short_name, then to empty', () => {
+  assert.equal(parseName({ name: '_', short_name: '_S_1_' }), 'S 1');
+  assert.equal(parseName({ name: '__', short_name: '_' }), '');
+});
+
+test('underscores are read the same in GBFS v3 localized names', () => {
+  assert.equal(
+    parseName(
+      {
+        name: [
+          { language: 'es', text: '_' },
+          { language: 'en', text: '_COLON_I' },
+        ],
+      },
+      '3.0',
+    ),
+    'COLON I',
+  );
+});
+
 test('GBFS v3 station names prefer English over the first translation', () => {
   assert.equal(
     parseName(