Fixes #9, set schema fix

sql/2023-11-21-clone-schema.sql

@@ -1 +1 @@
-SELECT clone_schema('louis_v005', '"louis_0.0.6"', TRUE);
+SELECT clone_schema('louis_v005', '"louis_0.0.6"', TRUE);

sql/2023-11-23-create-chunk-score-table.sql

@@ -2,4 +2,4 @@ CREATE TABLE chunk_score (
     id uuid default uuid_generate_v4 (),
     score FLOAT,
     score_type VARCHAR(50)
-);
+);

sql/2023-11-23-fill-chunk-score-table.sql

@@ -18,7 +18,7 @@ BEGIN
 SELECT
     COUNT(*) INTO tr_count
 FROM
-    "louis_0.0.6".chunk
+    chunk
 WHERE
     id = chunk_id
     AND html_content LIKE '%<tr>%';
@@ -28,4 +28,4 @@ RETURN tr_count;
 
 END;
 
-$ $ LANGUAGE plpgsql;
+$ $ LANGUAGE plpgsql;

sql/2023-11-28-chunk-didactic-score.sql

@@ -1,4 +1,4 @@
--- Set the search path to the louis_006 schema
+-- Set the search path to the louis_0.0.6 schema
 SET
     search_path TO "louis_0.0.6";
 
@@ -25,9 +25,9 @@ SELECT
     ) AS tr_proportion,
     'didactic' AS score_type
 FROM
-    "louis_0.0.6".chunk ch
-    INNER JOIN "louis_0.0.6".html_content_to_chunk hctc ON ch.id = hctc.chunk_id
-    INNER JOIN "louis_0.0.6".html_content hc ON hctc.md5hash = hc.md5hash
+    chunk ch
+    INNER JOIN html_content_to_chunk hctc ON ch.id = hctc.chunk_id
+    INNER JOIN html_content hc ON hctc.md5hash = hc.md5hash
     CROSS JOIN (
         SELECT
             MIN(
@@ -37,9 +37,9 @@ FROM
                 LENGTH(content) - LENGTH(REPLACE(content, '<tr>', ''))
             ) / LENGTH('<tr>') AS max_val
         FROM
-            "louis_0.0.6".chunk ch
-            INNER JOIN "louis_0.0.6".html_content_to_chunk hctc ON ch.id = hctc.chunk_id
-            INNER JOIN "louis_0.0.6".html_content hc ON hctc.md5hash = hc.md5hash
+            chunk ch
+            INNER JOIN html_content_to_chunk hctc ON ch.id = hctc.chunk_id
+            INNER JOIN html_content hc ON hctc.md5hash = hc.md5hash
     ) AS length_values
 ORDER BY
-    tr_proportion DESC;
+    tr_proportion DESC;

sql/2023-11-28-create-histogram.sql

@@ -1,10 +1,13 @@
--- Set the search path to the louis_006 schema
-SET search_path TO "louis_0.0.6";
-
+-- Set the search path to the louis_0.0.6 schema
+SET
+    search_path TO "louis_0.0.6";
+
 WITH tr_counts AS (
     SELECT
         c.id,
-        (LENGTH(h.content) - LENGTH(REPLACE(h.content, '<tr>', ''))) / LENGTH('<tr>') AS tr_count
+        (
+            LENGTH(h.content) - LENGTH(REPLACE(h.content, '<tr>', ''))
+        ) / LENGTH('<tr>') AS tr_count
     FROM
         crawl c
         INNER JOIN html_content h ON c.md5hash = h.md5hash
@@ -23,28 +26,50 @@ histogram AS (
         bucket_min,
         bucket_max,
         COUNT(t.score) AS freq,
-        REPEAT('■', 
-            (COUNT(t.score)::FLOAT / GREATEST(MAX(COUNT(t.score)) OVER(), 1) * 30)::INT
+        REPEAT(
+            '■',
+            (
+                COUNT(t.score) :: FLOAT / GREATEST(MAX(COUNT(t.score)) OVER(), 1) * 30
+            ) :: INT
         ) AS bar
-    FROM (
-        SELECT
-            CAST(generate_series(0, 9) AS FLOAT) / 10.0 AS bucket_min,
-            CAST(generate_series(1, 10) AS FLOAT) / 10.0 AS bucket_max
-    ) AS buckets
-    LEFT JOIN (
-        SELECT
-            id,
-            tr_count,
-            CASE
-                WHEN max_tr_count = min_tr_count THEN 0.0
-                ELSE 1.0 - ((tr_count - min_tr_count)::FLOAT / (max_tr_count - min_tr_count))
-            END AS score
-        FROM
-            tr_stats
-    ) t ON t.score >= buckets.bucket_min AND
-           (t.score < buckets.bucket_max OR
-            (buckets.bucket_max = 1.0 AND t.score <= buckets.bucket_max))
-    GROUP BY buckets.bucket_min, buckets.bucket_max
-    ORDER BY buckets.bucket_min, buckets.bucket_max
+    FROM
+        (
+            SELECT
+                CAST(generate_series(0, 9) AS FLOAT) / 10.0 AS bucket_min,
+                CAST(generate_series(1, 10) AS FLOAT) / 10.0 AS bucket_max
+        ) AS buckets
+        LEFT JOIN (
+            SELECT
+                id,
+                tr_count,
+                CASE
+                    WHEN max_tr_count = min_tr_count THEN 0.0
+                    ELSE 1.0 - (
+                        (tr_count - min_tr_count) :: FLOAT / (max_tr_count - min_tr_count)
+                    )
+                END AS score
+            FROM
+                tr_stats
+        ) t ON t.score >= buckets.bucket_min
+        AND (
+            t.score < buckets.bucket_max
+            OR (
+                buckets.bucket_max = 1.0
+                AND t.score <= buckets.bucket_max
+            )
+        )
+    GROUP BY
+        buckets.bucket_min,
+        buckets.bucket_max
+    ORDER BY
+        buckets.bucket_min,
+        buckets.bucket_max
 )
-SELECT bucket_min, bucket_max, freq, bar FROM histogram;
+SELECT
+    bucket_min,
+    bucket_max,
+    freq,
+    bar
+FROM
+    histogram;
+

sql/2023-11-28-print-schema-table.sql

@@ -1,3 +1,3 @@
 SELECT table_name, column_name, data_type
 FROM information_schema.columns
-WHERE table_schema = 'louis_006';
+WHERE table_schema = 'louis_0.0.6';

sql/2023-11-30-tr-count.sql

@@ -1,3 +1,7 @@
+-- Set the search path to the louis_0.0.6 schema
+SET
+    search_path TO "louis_0.0.6";
+
 WITH tr_counts AS (
     SELECT
         id,

sql/2023-12-11-score-by-element.sql

@@ -1,57 +1,4 @@
--- Set the search path to the louis_006 schema
-SET
-    search_path TO "louis_0.0.6";
-
-WITH tr_counts AS (
-    SELECT
-        id,
-        (LENGTH(h.content) - LENGTH(REPLACE(h.content, '<tr>', ''))) / LENGTH('<tr>') AS tr_count
-    FROM
-        crawl c
-        INNER JOIN html_content h ON c.md5hash = h.md5hash
-),
-tr_stats AS (
-    SELECT
-        id,
-        tr_count,
-        MAX(tr_count) OVER () AS max_tr_count,
-        MIN(tr_count) OVER () AS min_tr_count
-    FROM
-        tr_counts
-),
-histogram AS (
-    SELECT
-        bucket_min,
-        bucket_max,
-        COUNT(t.score) AS freq,
-        REPEAT('■', 
-            (COUNT(t.score)::FLOAT / GREATEST(MAX(COUNT(t.score)) OVER(), 1) * 30)::INT
-        ) AS bar
-    FROM (
-        SELECT
-            CAST(generate_series(0, 9) AS FLOAT) / 10.0 AS bucket_min,
-            CAST(generate_series(1, 10) AS FLOAT) / 10.0 AS bucket_max
-    ) AS buckets
-    LEFT JOIN (
-        SELECT
-            id,
-            tr_count,
-            CASE
-                WHEN max_tr_count = min_tr_count THEN 0.0
-                ELSE 1.0 - ((tr_count - min_tr_count)::FLOAT / (max_tr_count - min_tr_count))
-            END AS score
-        FROM
-            tr_stats
-    ) t ON t.score >= buckets.bucket_min AND
-           (t.score < buckets.bucket_max OR
-            (buckets.bucket_max = 1.0 AND t.score <= buckets.bucket_max))
-    GROUP BY buckets.bucket_min, buckets.bucket_max
-    ORDER BY buckets.bucket_min, buckets.bucket_max
-)
-SELECT bucket_min, bucket_max, freq, bar FROM histogram;
-
-
--- Set the search path to the louis_006 schema
+-- Set the search path to the louis_0.0.6 schema
 SET
     search_path TO "louis_0.0.6";
 

sql/2023-12-12-create-tabletest.sql

@@ -1,14 +1,14 @@
--- Set the search path to the louis_006 schema
+-- Set the search path to the louis_0.0.6 schema
 SET
     search_path TO "louis_0.0.6";
 
 CREATE TABLE  (
     content VARCHAR(255) -- Change 255 to the desired length of the string
 );
 
-TRUNCATE TABLE "louis_0.0.6".tabletest;
+TRUNCATE TABLE tabletest;
 
-CREATE TABLE "louis_0.0.6".tabletest (
+CREATE TABLE tabletest (
     id SERIAL PRIMARY KEY,
     html_content TEXT
 );