fix: adjusted regex for splits

CKudella · CKudella · commit e2b3a425e4ef · 2026-06-12T15:22:18.000+02:00
diff --git a/pirckheimer/sql_queries/corpus_overview/all_splits_in_wpirck_corpus.sql b/pirckheimer/sql_queries/corpus_overview/all_splits_in_wpirck_corpus.sql
@@ -1,3 +1,3 @@
 SELECT *
 FROM wpirck_cdb.letters
-WHERE letters_id REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id REGEXP 'ck[2-8]$'
diff --git a/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_from_to_pirck.sql b/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_from_to_pirck.sql
@@ -11,4 +11,4 @@ SELECT COUNT(CASE
                        WHEN l.recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080' THEN 1
                    END) * 100.0 / COUNT(*), 1) AS 'Percentage of the number of letters written to Pirckheimer of the total number of letters in the dataset'
 FROM wpirck_cdb.letters AS l
-WHERE l.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE l.letters_id NOT REGEXP 'ck[2-8]$'
diff --git a/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_language.sql b/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_language.sql
@@ -3,8 +3,8 @@ SELECT letter_language AS 'Letter Language',
        ROUND(COUNT(*) * 100.0 /
                (SELECT COUNT(*)
                 FROM wpirck_cdb.letters
-                WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'), 1) AS 'Percentage'
+                WHERE letters_id NOT REGEXP 'ck[2-8]$'), 1) AS 'Percentage'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY letter_language
 ORDER BY 'Percentage' DESC
diff --git a/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_type_genus.sql b/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_type_genus.sql
@@ -3,8 +3,8 @@ SELECT letter_type_genus,
        ROUND(COUNT(*) * 100.0 /
                (SELECT COUNT(*)
                 FROM wpirck_cdb.letters
-                WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'), 1) AS 'Percentage'
+                WHERE letters_id NOT REGEXP 'ck[2-8]$'), 1) AS 'Percentage'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY letter_type_genus
 ORDER BY 'Percentage' DESC
diff --git a/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_type_x_to_x.sql b/pirckheimer/sql_queries/corpus_overview/no_and_percentage_epp_in_db_excl_splits_by_letter_type_x_to_x.sql
@@ -3,8 +3,8 @@ SELECT letter_type_x_to_x,
        ROUND(COUNT(*) * 100.0 /
                (SELECT COUNT(*)
                 FROM wpirck_cdb.letters
-                WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'), 1) AS 'Percentage'
+                WHERE letters_id NOT REGEXP 'ck[2-8]$'), 1) AS 'Percentage'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY letter_type_x_to_x
 ORDER BY 'Percentage' DESC
diff --git a/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_excl_splits.sql b/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_excl_splits.sql
@@ -1,3 +1,3 @@
 SELECT COUNT(*) AS 'Number of letters in Pirckheimer DB'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
diff --git a/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_from_pirckheimer_bw_excl_splits.sql b/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_from_pirckheimer_bw_excl_splits.sql
@@ -2,5 +2,5 @@ SELECT COUNT(*) AS 'Total number of letters in DB that are part of the Pirckheim
 FROM wpirck_cdb.letters
 WHERE (letters_id LIKE 'wpirck_bw%'
        OR letter_no_in_edition LIKE '%[Pirckheimer BW]%')
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
 ORDER BY letters_id
diff --git a/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_not_from_pirckheimer_bw_excl_splits.sql b/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_not_from_pirckheimer_bw_excl_splits.sql
@@ -2,5 +2,5 @@ SELECT COUNT(*) AS 'Total number of letters in DB that are not part of the Pirck
 FROM wpirck_cdb.letters
 WHERE letters_id NOT LIKE 'wpirck_bw%'
   AND letter_no_in_edition NOT LIKE '%[Pirckheimer BW]%'
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
 ORDER BY letters_id
diff --git a/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_sent_by_pirck_excl_splits.sql b/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_sent_by_pirck_excl_splits.sql
@@ -1,4 +1,4 @@
 SELECT COUNT(*) AS 'Total number of letters sent by Pirckheimer'
 FROM wpirck_cdb.letters
 WHERE sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
diff --git a/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_sent_to_pirck_excl_splits.sql b/pirckheimer/sql_queries/corpus_overview/no_epp_in_db_sent_to_pirck_excl_splits.sql
@@ -1,4 +1,4 @@
 SELECT COUNT(*) AS 'Total number of letters sent to Pirckheimer'
 FROM wpirck_cdb.letters
 WHERE recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
diff --git a/pirckheimer/sql_queries/corpus_overview/no_locs_epp_written_by_pirck_at.sql b/pirckheimer/sql_queries/corpus_overview/no_locs_epp_written_by_pirck_at.sql
@@ -1,5 +1,5 @@
 SELECT COUNT(DISTINCT letters.source_loc_id) AS 'Total number of locations from which letters have been sent by Pirckheimer'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
   AND source_loc_id NOT LIKE 'unknown%'
diff --git a/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred.sql b/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred.sql
@@ -8,14 +8,14 @@ LEFT OUTER JOIN
   (SELECT XA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoInferred
    FROM wpirck_cdb.letters AS XA
-   WHERE XA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE XA.letters_id NOT REGEXP 'ck[2-8]$'
      AND XA.send_date_inferred = '1'
    GROUP BY XA.send_date_year1) AS X ON X.Year = Z.Year
 LEFT OUTER JOIN
   (SELECT YA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoNonInferred
    FROM wpirck_cdb.letters YA
-   WHERE YA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE YA.letters_id NOT REGEXP 'ck[2-8]$'
      AND YA.send_date_inferred = '0'
    GROUP BY YA.send_date_year1) AS Y ON Y.Year = Z.Year
 ORDER BY Z.Year ASC
diff --git a/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred_sent_from_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred_sent_from_pirck.sql
@@ -8,15 +8,15 @@ LEFT OUTER JOIN
   (SELECT DISTINCT XA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoInferred
    FROM wpirck_cdb.letters AS XA
-   WHERE XA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE XA.letters_id NOT REGEXP 'ck[2-8]$'
      AND XA.send_date_inferred = '1'
      AND XA.sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY XA.send_date_year1) AS X ON X.Year = Z.Year
 LEFT OUTER JOIN
   (SELECT DISTINCT YA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoNonInferred
    FROM wpirck_cdb.letters YA
-   WHERE YA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE YA.letters_id NOT REGEXP 'ck[2-8]$'
      AND YA.send_date_inferred = '0'
      AND YA.sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY YA.send_date_year1) AS Y ON Y.Year = Z.Year
diff --git a/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred_sent_to_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_inferred_noninferred_sent_to_pirck.sql
@@ -8,15 +8,15 @@ LEFT OUTER JOIN
   (SELECT DISTINCT XA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoInferred
    FROM wpirck_cdb.letters AS XA
-   WHERE XA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE XA.letters_id NOT REGEXP 'ck[2-8]$'
      AND XA.send_date_inferred = '1'
      AND XA.recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY XA.send_date_year1) AS X ON X.Year = Z.Year
 LEFT OUTER JOIN
   (SELECT DISTINCT YA.send_date_year1 AS YEAR,
                    COUNT(*) AS NoNonInferred
    FROM wpirck_cdb.letters YA
-   WHERE YA.letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE YA.letters_id NOT REGEXP 'ck[2-8]$'
      AND YA.send_date_inferred = '0'
      AND YA.recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY YA.send_date_year1) AS Y ON Y.Year = Z.Year
diff --git a/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_sent_by_to_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/comp_no_epp_per_year_sent_by_to_pirck.sql
@@ -4,24 +4,24 @@ SELECT DISTINCT A.send_date_year1,
 FROM
   (SELECT DISTINCT send_date_year1
    FROM wpirck_cdb.letters
-   WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE letters_id NOT REGEXP 'ck[2-8]$'
      AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    UNION ALL SELECT DISTINCT send_date_year1
    FROM wpirck_cdb.letters
-   WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE letters_id NOT REGEXP 'ck[2-8]$'
      AND recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080') AS A
 LEFT OUTER JOIN
   (SELECT send_date_year1,
           COUNT(*) AS NoEppSentFromPirck
    FROM wpirck_cdb.letters
-   WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE letters_id NOT REGEXP 'ck[2-8]$'
      AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY send_date_year1) AS B ON B.send_date_year1 = A.send_date_year1
 LEFT OUTER JOIN
   (SELECT send_date_year1,
           COUNT(*) AS NoEppSentToPirck
    FROM wpirck_cdb.letters
-   WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+   WHERE letters_id NOT REGEXP 'ck[2-8]$'
      AND recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
    GROUP BY send_date_year1) AS C ON C.send_date_year1 = A.send_date_year1
 ORDER BY A.send_date_year1 ASC
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_day_sent_by_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_day_sent_by_pirck.sql
@@ -2,5 +2,5 @@ SELECT DISTINCT send_date_computable1,
                 COUNT(*) AS NoEppSentFromPirck
 FROM wpirck_cdb.letters
 WHERE sender_id ='d9233b24-a98c-4279-8065-e2ab70c0d080'
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY send_date_computable1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_day_sent_to_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_day_sent_to_pirck.sql
@@ -2,5 +2,5 @@ SELECT DISTINCT send_date_computable1,
                 COUNT(*) AS NoEppSentToPirck
 FROM wpirck_cdb.letters
 WHERE recipient_id ='d9233b24-a98c-4279-8065-e2ab70c0d080'
-  AND letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+  AND letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY send_date_computable1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_send_date_year1.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_send_date_year1.sql
@@ -1,5 +1,5 @@
 SELECT send_date_year1,
        COUNT(*) AS 'Total number of letters sent this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_sent_by_pirck_send_date_year1.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_sent_by_pirck_send_date_year1.sql
@@ -1,6 +1,6 @@
 SELECT send_date_year1 AS YEAR,
        COUNT(*) AS 'Number of letters sent by Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_sent_to_pirck_send_date_year1.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_sent_to_pirck_send_date_year1.sql
@@ -1,6 +1,6 @@
 SELECT send_date_year1 AS YEAR,
        COUNT(*) AS 'Number of letters sent to Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date.sql
@@ -1,6 +1,6 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with inferred send date sent this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '1'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date_sent_by_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date_sent_by_pirck.sql
@@ -1,7 +1,7 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with inferred send date sent by Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '1'
   AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date_sent_to_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_inferred_send_date_sent_to_pirck.sql
@@ -1,7 +1,7 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with inferred send date sent to Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '1'
   AND recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date.sql
@@ -1,6 +1,6 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with non-inferred send date sent this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '0'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date_sent_by_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date_sent_by_pirck.sql
@@ -1,7 +1,7 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with non-inferred send date sent by Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '0'
   AND sender_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
diff --git a/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date_sent_to_pirck.sql b/pirckheimer/sql_queries/no_epp_per_year/no_epp_per_year_with_non_inferred_send_date_sent_to_pirck.sql
@@ -1,7 +1,7 @@
 SELECT DISTINCT send_date_year1 AS 'Year',
                 COUNT(letters_id) AS 'Number of letters with non-inferred send date sent to Pirckheimer this year'
 FROM wpirck_cdb.letters
-WHERE letters_id NOT REGEXP '[0-7]ck2|ck3|ck4|ck5|ck6|ck7|ck8'
+WHERE letters_id NOT REGEXP 'ck[2-8]$'
   AND send_date_inferred = '0'
   AND recipient_id = 'd9233b24-a98c-4279-8065-e2ab70c0d080'
 GROUP BY send_date_year1
