Class: StructuredDataToSql::MysqlDumpXml::TableDiscovery

Inherits:
Object
  • Object
show all
Defined in:
lib/structured_data_to_sql/mysql_dump_xml/table_discovery.rb

Defined Under Namespace

Classes: DiscoveryProgress, FileResult, Result, TableTagScanner

Constant Summary collapse

CDATA_START =
"<![CDATA[".b
CDATA_END =
"]]>".b
COMMENT_START =
"<!--".b
COMMENT_END =
"-->".b
PROCESSING_START =
"<?".b
PROCESSING_END =
"?>".b
TABLE_DATA_END_START =
"</table_data".b
DOCUMENT_MARKER =
/<\s*(?:table_structure|table_data|options)\b|<!\[CDATA\[|<!--|<\?/n
TABLE_DATA_MARKER =
%r{<!\[CDATA\[|<!--|<\?|</table_data\b}n
TAG_NAME =
/\A<\s*([A-Za-z_:][\w:.-]*)/n
ATTR =
/\b([A-Za-z_:][\w:.-]*)\s*=\s*(['"])(.*?)\2/mn
SCAN_TAIL_BYTES =
64

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(include_files: nil, exclude_files: nil, chunk_size: 1024 * 1024, max_bytes: nil) ⇒ TableDiscovery

Returns a new instance of TableDiscovery.



67
68
69
70
71
72
73
74
75
76
77
# File 'lib/structured_data_to_sql/mysql_dump_xml/table_discovery.rb', line 67

def initialize(
  include_files: nil,
  exclude_files: nil,
  chunk_size: 1024 * 1024,
  max_bytes: nil
)
  @include_files = include_files&.to_set
  @exclude_files = Array(exclude_files).to_set
  @chunk_size = chunk_size
  @max_bytes = max_bytes
end

Class Method Details

.size_metadata?(metadata) ⇒ Boolean

Returns:

  • (Boolean)


157
158
159
160
# File 'lib/structured_data_to_sql/mysql_dump_xml/table_discovery.rb', line 157

def self.size_metadata?()
   &&
    (.key?(:data_length) || .key?(:index_length))
end

.total_size(metadata) ⇒ Object



151
152
153
154
155
# File 'lib/structured_data_to_sql/mysql_dump_xml/table_discovery.rb', line 151

def self.total_size()
  return 0 unless 

  .values_at(:data_length, :index_length).compact.sum
end

Instance Method Details

#discover(source, file_pattern: "*.xml", progress_callback: nil, on_progress: nil, progress_interval: 5, input_gzip: false) ⇒ Object



79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
# File 'lib/structured_data_to_sql/mysql_dump_xml/table_discovery.rb', line 79

def discover(
  source,
  file_pattern: "*.xml",
  progress_callback: nil,
  on_progress: nil,
  progress_interval: 5,
  input_gzip: false
)
  files, temporary_inputs =
    IOSupport.discover(
      source,
      patterns: [file_pattern, "#{file_pattern}.gz"].uniq,
      stream_extension: ".xml",
      input_gzip:
    )
  raise UsageError, "No XML files found in #{source}" if files.empty?

  selected, skipped = files.partition { |file| process_file?(file) }
  if selected.empty?
    raise UsageError,
          "No XML files to scan after filtering. All #{files.length} files were excluded."
  end

  progress =
    DiscoveryProgress.new(
      callback: progress_callback,
      on_progress: on_progress,
      interval: progress_interval,
      total_input_bytes:
        selected.sum do |file|
          begin
            file.size
          rescue StandardError
            0
          end
        end
    )
  progress.report(:start, force: true, file_count: selected.length)

  file_results =
    selected.each_with_index.map do |file, index|
      progress.start_file(file, index: index + 1, count: selected.length)
      tables, , bytes_scanned, truncated =
        discover_file(file, progress: progress)
      progress.finish_file(force: true)
      FileResult.new(
        path: file,
        tables: tables.sort,
        table_metadata: ,
        bytes_scanned: bytes_scanned,
        truncated: truncated
      )
    end
  result =
    Result.new(
      tables: file_results.flat_map(&:tables).uniq.sort,
      files: file_results,
      files_found: files.length,
      files_skipped: skipped.length,
      skipped: skipped,
      table_metadata: (file_results),
      bytes_scanned: file_results.sum(&:bytes_scanned),
      truncated: file_results.any?(&:truncated)
    )
  progress.report(:complete, force: true, tables: result.tables.length)
  result
rescue StructuredDataToSql::InputError => e
  raise MysqlDumpXml::InputError, e.message
ensure
  temporary_inputs&.each(&:unlink)
end