Pull in set of reserved words from Redshift docs (sqlalchemy-redshift…

…#117)

Pull in set of reserved words from Redshift docs

Addresses sqlalchemy-redshift#94

CHANGES.rst

@@ -13,6 +13,8 @@
   (`Issue #110 <https://github.com/sqlalchemy-redshift/sqlalchemy-redshift/issues/110>`_)
 - Allow tests to tolerate new default column encodings in Redshift
   (`Issue #114 <https://github.com/sqlalchemy-redshift/sqlalchemy-redshift/pull/114>`_)
+- Pull in set of reserved words from Redshift docs
+  (`Issue #94 <https://github.com/sqlalchemy-redshift/sqlalchemy-redshift/issues/94>` _)
 
 
 0.5.0 (2016-04-21)

pull_reserved_words.sh

@@ -0,0 +1,17 @@
+#!/usr/bin/env sh
+
+## Scrapes a list of Redshift reserved words from AWS docs
+## and formats for copying and pasting into Python code.
+
+## This was developed on macOS and may not directly translate to
+## other platforms.
+
+curl "https://docs.aws.amazon.com/redshift/latest/dg/r_pg_keywords.html" \
+    | tr '\n' '\r' \
+    | sed 's/.*\(AES128.*WITHOUT\).*/\1/' \
+    | tr '\r' '\n' \
+    | sed 's/^\([A-Z0-9_]*\).*/"\1",/' \
+    | paste -s -d' ' - \
+    | fold -s -w 70 \
+    | awk '{print "    "$0}' \
+    | tr 'A-Z' 'a-z'

sqlalchemy_redshift/dialect.py

@@ -4,7 +4,9 @@
 import pkg_resources
 import sqlalchemy as sa
 from sqlalchemy import Column, exc, inspect
-from sqlalchemy.dialects.postgresql.base import PGCompiler, PGDDLCompiler
+from sqlalchemy.dialects.postgresql.base import (
+    PGCompiler, PGDDLCompiler, PGIdentifierPreparer
+)
 from sqlalchemy.dialects.postgresql.psycopg2 import PGDialect_psycopg2
 from sqlalchemy.engine import reflection
 from sqlalchemy.ext.compiler import compiles
@@ -96,6 +98,36 @@ class RedshiftImpl(postgresql.PostgresqlImpl):
   \s* \) \s*                # Arbitrary whitespace and literal ')'
 """, re.VERBOSE)
 
+# Reserved words as extracted from Redshift docs.
+# See pull_reserved_words.sh at the top level of this repository
+# for the code used to generate this set.
+RESERVED_WORDS = set([
+    "aes128", "aes256", "all", "allowoverwrite", "analyse", "analyze",
+    "and", "any", "array", "as", "asc", "authorization", "backup",
+    "between", "binary", "blanksasnull", "both", "bytedict", "bzip2",
+    "case", "cast", "check", "collate", "column", "constraint", "create",
+    "credentials", "cross", "current_date", "current_time",
+    "current_timestamp", "current_user", "current_user_id", "default",
+    "deferrable", "deflate", "defrag", "delta", "delta32k", "desc",
+    "disable", "distinct", "do", "else", "emptyasnull", "enable",
+    "encode", "encrypt", "encryption", "end", "except", "explicit",
+    "false", "for", "foreign", "freeze", "from", "full", "globaldict256",
+    "globaldict64k", "grant", "group", "gzip", "having", "identity",
+    "ignore", "ilike", "in", "initially", "inner", "intersect", "into",
+    "is", "isnull", "join", "leading", "left", "like", "limit",
+    "localtime", "localtimestamp", "lun", "luns", "lzo", "lzop", "minus",
+    "mostly13", "mostly32", "mostly8", "natural", "new", "not",
+    "notnull", "null", "nulls", "off", "offline", "offset", "oid", "old",
+    "on", "only", "open", "or", "order", "outer", "overlaps", "parallel",
+    "partition", "percent", "permissions", "placing", "primary", "raw",
+    "readratio", "recover", "references", "respect", "rejectlog",
+    "resort", "restore", "right", "select", "session_user", "similar",
+    "snapshot", "some", "sysdate", "system", "table", "tag", "tdes",
+    "text255", "text32k", "then", "timestamp", "to", "top", "trailing",
+    "true", "truncatecolumns", "union", "unique", "user", "using",
+    "verbose", "wallet", "when", "where", "with", "without",
+])
+
 
 class RelationKey(namedtuple('RelationKey', ('name', 'schema'))):
     """
@@ -312,6 +344,10 @@ def _fetch_redshift_column_attributes(self, column):
         return text
 
 
+class RedshiftIdentifierPreparer(PGIdentifierPreparer):
+    reserved_words = RESERVED_WORDS
+
+
 class RedshiftDialect(PGDialect_psycopg2):
     """
     Define Redshift-specific behavior.
@@ -326,6 +362,7 @@ class RedshiftDialect(PGDialect_psycopg2):
 
     statement_compiler = RedshiftCompiler
     ddl_compiler = RedshiftDDLCompiler
+    preparer = RedshiftIdentifierPreparer
     construct_arguments = [
         (sa.schema.Index, {
             "using": False,

tests/rs_sqla_test_utils/models.py

@@ -159,6 +159,16 @@ class ReflectionDelimitedIdentifiers2(Base):
     )
 
 
+class ReflectionCustomReservedWords(Base):
+    __tablename__ = 'aes256'
+    col1 = sa.Column('open', sa.Integer())
+    col2 = sa.Column('tag', sa.Integer())
+    pkey = sa.Column('pkey', sa.Integer(), primary_key=True)
+    __table_args__ = (
+        {'redshift_diststyle': 'EVEN'}
+    )
+
+
 class ReflectionDelimitedTableName(Base):
     __tablename__ = 'this.table'
     col1 = sa.Column('id', sa.Integer(), primary_key=True)

tests/test_reflection.py

@@ -111,6 +111,14 @@ def table_to_ddl(table):
             PRIMARY KEY ("excellent! & column"),
     ) DISTSTYLE EVEN
     ''')),
+    (models.ReflectionCustomReservedWords, '''
+    CREATE TABLE "aes256" (
+        "open" INTEGER,
+        "tag" INTEGER,
+        pkey INTEGER NOT NULL,
+        PRIMARY KEY (pkey)
+    ) DISTSTYLE EVEN
+    '''),
     (models.Referencing, '''
     CREATE TABLE other_schema.referencing (
         referenced_table_id INTEGER NOT NULL,