[FIX] PARTITION BY with newline not properly formatted (#138)

PabloRMira · Jan 22, 2021 · 4ec4b93 · 4ec4b93
1 parent 64ee02a
commit 4ec4b93
Show file tree

Hide file tree

Showing 7 changed files with 346 additions and 48 deletions.
diff --git a/docs/core.html b/docs/core.html
diff --git a/docs/utils.html b/docs/utils.html
diff --git a/nbs/00_core.ipynb b/nbs/00_core.ipynb
@@ -201,6 +201,7 @@
     "    s = replace_newline_chars(s)  # remove newlines but not in the comments\n",
     "    s = remove_whitespaces_newline(s)  # remove whitespaces after and before newline\n",
     "    s = remove_whitespaces_comments(s)  # remove whitespaces after and before [C], [CS] and [CI]\n",
+    "    s = remove_whitespaces_parenthesis(s)  # remove whitespaces between parenthesis\n",
     "    s = remove_redundant_whitespaces(s)  # remove too many whitespaces but no newlines\n",
     "    return s"
    ]
@@ -351,6 +352,34 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "create or replace table my_table as select substr(asdf, 1, 2) as qwer, qwer over (PARTITION BY asdf) from table1\n"
+     ]
+    }
+   ],
+   "source": [
+    "assert_and_print(\n",
+    "    clean_query(\n",
+    "\"\"\"\n",
+    "create or replace table my_table as\n",
+    "select substr( asdf, 1, 2 ) as qwer,\n",
+    "qwer over (\n",
+    "PARTITION BY asdf\n",
+    ")\n",
+    "from table1\n",
+    "\"\"\"\n",
+    "    ), \"create or replace table my_table as select substr(asdf, 1, 2) as qwer, qwer over (PARTITION BY asdf) from table1\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -3302,6 +3331,51 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Partition By with newline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CREATE OR REPLACE TABLE asdf AS\n",
+      "SELECT asdf,\n",
+      "       qwer OVER (PARTITION BY asdf,\n",
+      "                               qwer\n",
+      "                  ORDER BY qwerty)\n",
+      "FROM   table1\n"
+     ]
+    }
+   ],
+   "source": [
+    "assert_and_print(\n",
+    "format_sql(\"\"\"\n",
+    "create or replace table asdf as\n",
+    "select asdf, qwer over (\n",
+    "partition by asdf, qwer order by qwerty\n",
+    ")\n",
+    "from table1\n",
+    "\"\"\"),\n",
+    "\"\"\"\n",
+    "CREATE OR REPLACE TABLE asdf AS\n",
+    "SELECT asdf,\n",
+    "       qwer OVER (PARTITION BY asdf,\n",
+    "                               qwer\n",
+    "                  ORDER BY qwerty)\n",
+    "FROM   table1\n",
+    "\"\"\".strip()\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

diff --git a/nbs/02_utils.ipynb b/nbs/02_utils.ipynb
@@ -353,6 +353,40 @@
     ")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#export\n",
+    "def remove_whitespaces_parenthesis(s):\n",
+    "    \"Remove whitespaces between parenthesis in query `s`\"\n",
+    "    s = re.sub(r\"\\([\\r\\t\\f\\v ]+\", \"(\", s)  # remove whitespaces after (\n",
+    "    s = re.sub(r\"[\\r\\t\\f\\v ]+\\)\", \")\", s)  # remove whitespaces before )\n",
+    "    return s"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "select asdf, substr(qwer, 1, 2) as qwerty\n"
+     ]
+    }
+   ],
+   "source": [
+    "assert_and_print(\n",
+    "    remove_whitespaces_parenthesis(\"select asdf, substr( qwer, 1, 2 ) as qwerty\"),\n",
+    "    \"select asdf, substr(qwer, 1, 2) as qwerty\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -2450,7 +2484,20 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Converted 00_core.ipynb.\n",
+      "Converted 01_format_file.ipynb.\n",
+      "Converted 02_utils.ipynb.\n",
+      "Converted 03_validation.ipynb.\n",
+      "Converted 04_release.ipynb.\n",
+      "Converted index.ipynb.\n"
+     ]
+    }
+   ],
    "source": [
     "#hide\n",
     "from nbdev.export import notebook2script\n",

diff --git a/sql_formatter/_nbdev.py b/sql_formatter/_nbdev.py
@@ -28,6 +28,7 @@
          "remove_whitespaces_newline": "02_utils.ipynb",
          "remove_whitespaces_comments": "02_utils.ipynb",
          "remove_redundant_whitespaces": "02_utils.ipynb",
+         "remove_whitespaces_parenthesis": "02_utils.ipynb",
          "add_whitespaces_between_symbols": "02_utils.ipynb",
          "mark_ci_comments": "02_utils.ipynb",
          "mark_comments": "02_utils.ipynb",

diff --git a/sql_formatter/core.py b/sql_formatter/core.py
@@ -37,6 +37,7 @@ def clean_query(s):
     s = replace_newline_chars(s)  # remove newlines but not in the comments
     s = remove_whitespaces_newline(s)  # remove whitespaces after and before newline
     s = remove_whitespaces_comments(s)  # remove whitespaces after and before [C], [CS] and [CI]
+    s = remove_whitespaces_parenthesis(s)  # remove whitespaces between parenthesis
     s = remove_redundant_whitespaces(s)  # remove too many whitespaces but no newlines
     return s
 

diff --git a/sql_formatter/utils.py b/sql_formatter/utils.py
@@ -1,11 +1,12 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: nbs/02_utils.ipynb (unless otherwise specified).
 
 __all__ = ['assert_and_print', 'compress_dicts', 'remove_whitespaces_newline', 'remove_whitespaces_comments',
-           'remove_redundant_whitespaces', 'add_whitespaces_between_symbols', 'mark_ci_comments', 'mark_comments',
-           'split_query', 'split_apply_concat', 'split_comment_quote', 'split_comment', 'identify_in_sql',
-           'split_by_semicolon', 'replace_newline_chars', 'identify_end_of_fields', 'add_newline_indentation',
-           'extract_outer_subquery', 'format_subquery', 'check_sql_query', 'check_skip_marker',
-           'identify_create_table_view', 'count_lines', 'find_line_number', 'jaccard_distance', 'assign_comment']
+           'remove_redundant_whitespaces', 'remove_whitespaces_parenthesis', 'add_whitespaces_between_symbols',
+           'mark_ci_comments', 'mark_comments', 'split_query', 'split_apply_concat', 'split_comment_quote',
+           'split_comment', 'identify_in_sql', 'split_by_semicolon', 'replace_newline_chars', 'identify_end_of_fields',
+           'add_newline_indentation', 'extract_outer_subquery', 'format_subquery', 'check_sql_query',
+           'check_skip_marker', 'identify_create_table_view', 'count_lines', 'find_line_number', 'jaccard_distance',
+           'assign_comment']
 
 # Cell
 import re
@@ -82,6 +83,13 @@ def remove_redundant_whitespaces(s):
     s = re.sub(r"[\r\t\f\v ]{2,}", " ", s)  # remove too many whitespaces but not newlines
     return s
 
+# Cell
+def remove_whitespaces_parenthesis(s):
+    "Remove whitespaces between parenthesis in query `s`"
+    s = re.sub(r"\([\r\t\f\v ]+", "(", s)  # remove whitespaces after (
+    s = re.sub(r"[\r\t\f\v ]+\)", ")", s)  # remove whitespaces before )
+    return s
+
 # Cell
 def add_whitespaces_between_symbols(s):
     "Add whitespaces between symbols in line `s`"