Class: Exwiw::Adapter::PostgresqlAdapter

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 79

def build_query(table, dump_target, table_by_name)
  Exwiw::QueryAstBuilder.run(table.name, table_by_name, dump_target, @logger)
end

#compile_ast(query_ast, select_cast_to: nil) ⇒ `Object`

Raises:

(NotImplementedError)

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 282

def compile_ast(query_ast, select_cast_to: nil)
  raise NotImplementedError unless query_ast.is_a?(Exwiw::QueryAst::Select)

  # Lift scope id-set clauses (reverse_scope UNION / forward cascade /
  # single referenced_by) out of `WHERE <col> IN (subquery)` and into a
  # JOIN against a materialized derived table. See #compile_scope_join.
  scope_clauses, plain_where_clauses = partition_scope_clauses(query_ast.where_clauses)

  sql = "SELECT "
  sql += if query_ast.select_all
           # A lifted scope JOIN brings a derived table into FROM, so a bare
           # `*` would also project its column. Qualify to this table's own.
           scope_clauses.any? ? "#{query_ast.from_table_name}.*" : "*"
         else
           cols = query_ast.columns.map { |col| compile_column_name(query_ast, col) }
           cols = cols.map { |c| "#{c}::#{select_cast_to}" } if select_cast_to
           cols.join(', ')
         end
  sql += " FROM #{query_ast.from_table_name}"

  query_ast.join_clauses.each do |join|
    fk_expr = "#{join.base_table_name}.#{join.foreign_key}"
    pk_expr = "#{join.join_table_name}.#{join.primary_key}"
    if types_need_cast?(
      column_pg_type(join.base_table_name, join.foreign_key),
      column_pg_type(join.join_table_name, join.primary_key)
    )
      fk_expr = "#{fk_expr}::text"
      pk_expr = "#{pk_expr}::text"
    end
    sql += " JOIN #{join.join_table_name} ON #{fk_expr} = #{pk_expr}"

    join.where_clauses.each do |where|
      compiled_where_condition = compile_where_condition(where, join.join_table_name)
      sql += " AND #{compiled_where_condition}"
    end

    # base_where_clauses is compiled against the joined-from table
    # (base_table_name), e.g. the type-column filter on a polymorphic
    # source table.
    join.base_where_clauses.each do |where|
      compiled_where_condition = compile_where_condition(where, join.base_table_name)
      sql += " AND #{compiled_where_condition}"
    end
  end

  scope_clauses.each_with_index do |where_clause, idx|
    sql += " #{compile_scope_join(query_ast.from_table_name, where_clause, idx)}"
  end

  if plain_where_clauses.any?
    sql += " WHERE "
    sql += plain_where_clauses.map { |where| compile_where_condition(where, query_ast.from_table_name) }.join(' AND ')
  end

  sql
end

#dump_schema(ordered_tables, output_path) ⇒ `Object`

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 100

def dump_schema(ordered_tables, output_path)
  require 'open3'

  # Full-database schema dump: emit DDL for every table in the database,
  # not just the config-scoped tables. A table absent from the config
  # gets its schema here but no data (empty INSERT), which is the intended
  # result — the restore target then has every relation even when exwiw
  # was configured to extract only a subset, so a later reference to an
  # unscoped table does not fail with "relation does not exist".
  # `ordered_tables` no longer selects which tables are emitted; it is kept
  # only for the log line (how many tables are in scope for data).
  cmd = [
    'pg_dump',
    "--host=#{@connection_config.host}",
    "--port=#{@connection_config.port}",
    "--username=#{@connection_config.user}",
    '--schema-only',
    '--no-owner',
    '--no-acl',
    @connection_config.database_name,
  ]
  env = { 'PGPASSWORD' => @connection_config.password.to_s }

  @logger.debug("  Running pg_dump for the whole database (#{@connection_config.database_name})...")
  stdout, stderr, status = Open3.capture3(env, *cmd)
  unless status.success?
    if stderr.include?('command not found') || stderr.empty?
      raise "Failed to run `pg_dump`. Ensure the postgresql client is installed and on PATH. stderr: #{stderr}"
    end
    raise "pg_dump failed (exit #{status.exitstatus}): #{stderr}"
  end

  # A full-database dump emits CREATE EXTENSION and CREATE TYPE ... AS ENUM
  # itself (a `--table` dump omitted both, which is why they used to be
  # prepended by hand), but pg_dump's bare forms are neither idempotent nor
  # restore-tolerant. Wrap them in place to restore the previous
  # robustness: enums swallow duplicate_object on re-restore; extensions
  # warn-and-skip feature_not_supported / invalid_schema_name so a target
  # that cannot provide the extension (e.g. pglogical's schema absent, or a
  # managed-platform extension) does not abort the restore.
  idempotent = stdout
  idempotent = DdlPostprocessor.wrap_create_type_enum_in_do_block(idempotent)
  idempotent = DdlPostprocessor.wrap_create_extension_in_do_block(idempotent)
  idempotent = DdlPostprocessor.add_if_not_exists_to_create_schema(idempotent)
  idempotent = DdlPostprocessor.add_if_not_exists_to_create_sequence(idempotent)
  idempotent = DdlPostprocessor.add_if_not_exists_to_create_table(idempotent)
  idempotent = DdlPostprocessor.add_if_not_exists_to_create_index(idempotent)
  idempotent = DdlPostprocessor.wrap_add_constraint_in_do_block(idempotent)
  idempotent = DdlPostprocessor.strip_triggers(idempotent)

  File.open(output_path, 'w') do |file|
    file.puts("-- Auto-generated by exwiw via pg_dump. Idempotent DDL for postgresql.")
    file.write(idempotent)
  end
  @logger.info("  Wrote full-database schema to #{output_path} (#{ordered_tables.size} table(s) in scope for data).")
end

#execute(query_ast) ⇒ `Object`

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 83

def execute(query_ast)
  data_sql = commented_sql(query_ast)
  # Count via the same query (wrapped as a subquery) so the Runner can
  # skip empty tables and log the row count without draining the stream.
  count_sql = "#{sql_query_comment(query_ast)} SELECT COUNT(*) FROM (#{compile_ast(query_ast)}) AS exwiw_count_src"

  @logger.debug("  Executing SQL (single-row stream): \n#{data_sql}")
  StreamingResult.new(connection: connection, data_sql: data_sql, count_sql: count_sql)
end

#explain(query_ast, verbosity: nil) ⇒ `Object`

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 93

def explain(query_ast, verbosity: nil)
  sql = commented_sql(query_ast)

  @logger.debug("  Executing EXPLAIN: \n#{sql}")
  connection.exec("EXPLAIN #{sql}").values.map(&:first).join("\n")
end

#post_insert_sql(table) ⇒ `Object`

Transcribe the FROM-side sequence cursor backing table.primary_key onto the import target. Without this, importing into a clean DB leaves the sequence at 1 while the inserted rows occupy higher IDs, so the next default-PK INSERT collides. We query FROM's last_value / is_called directly (matching what pg_dump emits) rather than using MAX(pk), so a subsetted dump still preserves the source's "next id". Returns nil for non-auto-increment PKs (pg_get_serial_sequence -> NULL).

Scope: ONLY the sequence attached to the primary key is synced. If a table has additional auto-increment columns (e.g. a non-PK SERIAL), those sequences are NOT transcribed and a subsequent default-value INSERT on them can collide. Rails-managed schemas don't hit this because only id is auto-increment, but bare PostgreSQL schemas may.

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 198

def post_insert_sql(table)
  pk = table.primary_key
  return nil if pk.nil? || pk.empty?

  seq_name = connection
    .exec_params("SELECT pg_get_serial_sequence($1, $2)", [table.name, pk])
    .values.dig(0, 0)
  return nil if seq_name.nil?

  last_value, is_called = connection
    .exec("SELECT last_value, is_called FROM #{seq_name}")
    .values.first
  is_called_sql = (is_called == 't' || is_called == true) ? 'true' : 'false'

  "SELECT pg_catalog.setval('#{escape_single_quote(seq_name)}', #{last_value}, #{is_called_sql});"
end

#to_bulk_delete(select_query_ast, table) ⇒ `Object`

Raises:

(NotImplementedError)

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 215

def to_bulk_delete(select_query_ast, table)
  raise NotImplementedError unless select_query_ast.is_a?(Exwiw::QueryAst::Select)

  sql = "DELETE FROM #{select_query_ast.from_table_name}"

  if select_query_ast.join_clauses.empty?
    # Ignore filter option, because bulk delete is for cleaning before import,
    # so it should delete all records to avoid foreign key violation & data consistancy.
    compiled_where_conditions = select_query_ast.
      where_clauses.
      select { |where| where.is_a?(Exwiw::QueryAst::WhereClause) }.
      map do |where|
      compile_where_condition(where, select_query_ast.from_table_name)
    end

    if compiled_where_conditions.size > 0
      sql += "\nWHERE "
      sql += compiled_where_conditions.join(' AND ')
    end
    sql += ";"

    return sql
  end

  subquery_ast = Exwiw::QueryAst::Select.new
  first_join = select_query_ast.join_clauses.first.clone

  subquery_ast.from(first_join.join_table_name)
  primay_key_col = table.columns.find { |col| col.name == table.primary_key }
  subquery_ast.select([primay_key_col])
  select_query_ast.join_clauses[1..].each do |join|
    subquery_ast.join(join)
  end
  first_join.where_clauses.each do |where|
    # Ignore filter option, because bulk delete is for cleaning before import,
    # so it should delete all records to avoid foreign key violation & data consistancy.
    subquery_ast.where(where) if where.is_a?(Exwiw::QueryAst::WhereClause)
  end

  foreign_key = first_join.foreign_key
  outer_table = select_query_ast.from_table_name
  inner_table = first_join.join_table_name
  inner_column = first_join.primary_key
  cast_to = types_need_cast?(
    column_pg_type(outer_table, foreign_key),
    column_pg_type(inner_table, inner_column)
  ) ? 'text' : nil
  subquery_sql = compile_ast(subquery_ast, select_cast_to: cast_to)
  outer_expr = "#{outer_table}.#{foreign_key}"
  outer_expr = "#{outer_expr}::text" if cast_to
  sql += "\nWHERE #{outer_expr} IN (#{subquery_sql})"

  # first_join.base_where_clauses holds conditions on the outer
  # delete-target table (from_table_name), such as a polymorphic type
  # column. They are not part of the subquery, so add them to the outer
  # WHERE. This prevents deleting rows that belong to a different
  # polymorphic type.
  first_join.base_where_clauses.each do |where|
    next unless where.is_a?(Exwiw::QueryAst::WhereClause)

    sql += " AND #{compile_where_condition(where, select_query_ast.from_table_name)}"
  end
  sql += ";"

  sql
end

#to_copy_from_stdin(results, table) ⇒ `Object`

# File 'lib/exwiw/adapter/postgresql_adapter.rb', line 170

def to_copy_from_stdin(results, table)
  header = if table.rails_managed?
             "COPY #{table.name} FROM stdin;"
           else
             column_names = table.columns.map(&:name).join(', ')
             "COPY #{table.name} (#{column_names}) FROM stdin;"
           end
  lines = [header]
  results.each do |row|
    lines << row.map { |v| escape_copy_value(v) }.join("\t")
  end
  lines << '\\.'
  lines.join("\n")
end

Class: Exwiw::Adapter::PostgresqlAdapter

Defined Under Namespace

Constant Summary

Constants included from SqlBulkInsert

Instance Attribute Summary

Attributes inherited from Base

Instance Method Summary collapse

Methods included from SqlBulkInsert

Methods inherited from Base

Constructor Details

Instance Method Details

#build_query(table, dump_target, table_by_name) ⇒ Object

#compile_ast(query_ast, select_cast_to: nil) ⇒ Object

#dump_schema(ordered_tables, output_path) ⇒ Object

#execute(query_ast) ⇒ Object

#explain(query_ast, verbosity: nil) ⇒ Object

#post_insert_sql(table) ⇒ Object

#to_bulk_delete(select_query_ast, table) ⇒ Object

#to_copy_from_stdin(results, table) ⇒ Object