use a *much faster* SQL query

docs/gazette.md

@@ -7,7 +7,7 @@ const db = DuckDBClient.of({ presse: FileAttachment("data/presse.parquet") });
 
 This page allows you to explore the 3 million newspapers by title. I called it “Gazette” because I was surprised that most of the corpus in the earlier years had a title containing this word.
 
-Type in words such as “jeune”, “révolution”, “république”, “soir”, “fille”, “femme”, “paysan”, “ouvrier”, “social”, etc., to see different historical trends.
+Type in words such as “jeune”, “révolution”, “république”, “matin”, “soir”, “humanité”, “nouvelle”, “moderne”, “femme”, “paysan”, “ouvrier”, “social”, “résistance” etc. to see different historical trends.
 
 ```js
 const search = view(
@@ -15,41 +15,56 @@ const search = view(
 );
 ```
 
+${
+Plot.plot({
+x: { nice: true },
+y: {
+label: `Share of titles matching ${search}`,
+tickFormat: "%",
+},
+marks: [
+Plot.areaY(base, {
+x: "year",
+y: ({year, total}) => gazette.get(year) / total,
+fillOpacity: 0.2,
+curve: "step"
+}),
+Plot.lineY(base, {
+x: "year",
+y: ({year, total}) => gazette.get(year) / total,
+curve: "step"
+}),
+],
+})
+}
+
+The query uses a case-insensitive [REGEXP_MATCHES](https://duckdb.org/docs/archive/0.9.2/sql/functions/patternmatching) operator to count occurrences; you can query for example “socialis[tm]e” to match both “socialiste” and “socialisme”.
+
 ```js echo
-display(
-  Plot.plot({
-    x: { nice: true },
-    y: {
-      label: `Share of titles matching ${search}`,
-      tickFormat: "%",
-    },
-    marks: [
-      Plot.areaY(gazette, {
-        x: "year",
-        y: (d) => d.matches / d.total,
-        fillOpacity: 0.2,
-      }),
-      Plot.lineY(gazette, {
-        x: "year",
-        y: (d) => d.matches / d.total,
-      }),
-    ],
-  })
+const results = db.query(
+  `SELECT year, COUNT() c
+     FROM presse
+    WHERE REGEXP_MATCHES(title, ?, 'i')
+ GROUP BY year
+`,
+  [search]
 );
 ```
 
-The query uses the [REGEXP_MATCHES](https://duckdb.org/docs/archive/0.9.2/sql/functions/patternmatching) operator to count occurrences; you can query for example “socialis[tm]e” to match both “socialiste” and “socialisme”. The 'i' flag makes it ignore case.
+```js
+// A Map for fast retrieval—precisely an InternMap, indexed by Date
+const gazette = new d3.InternMap(results.map(({ year, c }) => [year, c]));
+```
 
-```js echo
-const gazette = db.query(
+```js
+// The base denominator (count by year)
+const base = db.query(
   `SELECT year
-       , SUM(CASE WHEN REGEXP_MATCHES(title, ?, 'i') THEN 1 ELSE 0 END)::int matches
-       , COUNT(*) total
+       , COUNT(*)::int total
     FROM presse
    WHERE year > '1000'
 GROUP BY year
 ORDER BY year
-`,
-  [search]
+`
 );
 ```