Add sqlfluff for formatting

Author: msj

.pre-commit-config.yaml

@@ -17,7 +17,7 @@ repos:
       - id: flake8
         args: [--config=.flake8]
 
-  # - repo: https://github.com/sqlfluff/sqlfluff
-  #   rev: 2.3.5
-  #   hooks:
-  #   -   id: sqlfluff-lint
+  - repo: https://github.com/sqlfluff/sqlfluff
+    rev: 2.3.5
+    hooks:
+    -   id: sqlfluff-lint

.sqlfluff

@@ -2,7 +2,7 @@
 
 # Supported dialects https://docs.sqlfluff.com/en/stable/dialects.html
 # Or run 'sqlfluff dialects'
-dialect = snowflake
+dialect = sqlite
 
 # One of [raw|jinja|python|placeholder]
 templater = jinja
@@ -17,7 +17,7 @@ exclude_rules = ambiguous.column_count, structure.column_order
 # other tools and several style guides. Many projects however prefer
 # something a little longer.
 # Set to zero or negative to disable checks.
-max_line_length = 120
+max_line_length = 80
 
 # CPU processes to use while linting.
 # The default is "single threaded" to allow easy debugging, but this

scripts/update.sql

@@ -1,36 +1,39 @@
 -- Given a CSV of re-scraped cases, update the matching cases in the database
 CREATE TEMPORARY TABLE raw_case (
-        ad_damnum text,
-        calendar text,
-        case_number text,
-        case_type text,
-        court text,
-        division text,
-        filing_date text,
-        hash text,
-        scraped_at text,
-        updated_at text
+    ad_damnum text,
+    calendar text,
+    case_number text,
+    case_type text,
+    court text,
+    division text,
+    filing_date text,
+    hash text,
+    scraped_at text,
+    updated_at text
 );
 
-.mode csv
-.import /dev/stdin raw_case
+.mode csv -- noqa
+.import /dev/stdin raw_case -- noqa
 
 -- Update cases that have changed (i.e. their hashes are different)
 UPDATE court_case
-SET calendar = raw_case.calendar,
-filing_date = raw_case.filing_date,
-division = raw_case.division,
-case_type = raw_case.case_type,
-ad_damnum = raw_case.ad_damnum,
-court = raw_case.court,
-hash = raw_case.hash,
-scraped_at = raw_case.scraped_at,
-updated_at = raw_case.scraped_at
+SET
+    calendar = raw_case.calendar,
+    filing_date = raw_case.filing_date,
+    division = raw_case.division,
+    case_type = raw_case.case_type,
+    ad_damnum = raw_case.ad_damnum,
+    court = raw_case.court,
+    hash = raw_case.hash,
+    scraped_at = raw_case.scraped_at,
+    updated_at = raw_case.scraped_at
 FROM raw_case
-WHERE court_case.case_number = raw_case.case_number and court_case.hash != raw_case.hash;
+WHERE
+    court_case.case_number = raw_case.case_number AND court_case.hash != raw_case.hash;
 
 -- For cases that haven't changed, just update their scraped_at field
 UPDATE court_case
 SET scraped_at = raw_case.scraped_at
-from raw_case
-where court_case.case_number = raw_case.case_number and court_case.hash = raw_case.hash;
+FROM raw_case
+WHERE
+    court_case.case_number = raw_case.case_number AND court_case.hash = raw_case.hash;