berkeley_library-tind 0.4.0 → 0.5.0

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: berkeley_library-tind
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - David Moles
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-08-19 00:00:00.000000000 Z
+date: 2022-02-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: berkeley_library-logging
@@ -30,14 +30,34 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: 0.3.0
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.2'
+        version: 0.3.0
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.3.1
+- !ruby/object:Gem::Dependency
+  name: berkeley_library-util
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
 - !ruby/object:Gem::Dependency
   name: ice_nine
   requirement: !ruby/object:Gem::Requirement
@@ -179,25 +199,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '2.7'
 - !ruby/object:Gem::Dependency
-  name: listen
+  name: equivalent-xml
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 3.0.5
-    - - "<"
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '0.6'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 3.0.5
-    - - "<"
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '0.6'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -360,7 +374,6 @@ files:
 - CHANGES.md
 - Dockerfile
 - Gemfile
-- Jenkinsfile
 - LICENSE.md
 - README.md
 - Rakefile
@@ -396,10 +409,11 @@ files:
 - lib/berkeley_library/tind/export/table.rb
 - lib/berkeley_library/tind/export/table_metrics.rb
 - lib/berkeley_library/tind/marc.rb
+- lib/berkeley_library/tind/marc/xml_builder.rb
 - lib/berkeley_library/tind/marc/xml_reader.rb
+- lib/berkeley_library/tind/marc/xml_writer.rb
 - lib/berkeley_library/tind/module_info.rb
-- lib/berkeley_library/util/arrays.rb
-- lib/berkeley_library/util/logging.rb
+- lib/berkeley_library/util/files.rb
 - lib/berkeley_library/util/ods/spreadsheet.rb
 - lib/berkeley_library/util/ods/xml/content_doc.rb
 - lib/berkeley_library/util/ods/xml/document_node.rb
@@ -439,15 +453,6 @@ files:
 - lib/berkeley_library/util/ods/xml/table/table_column.rb
 - lib/berkeley_library/util/ods/xml/table/table_row.rb
 - lib/berkeley_library/util/ods/xml/text/p.rb
-- lib/berkeley_library/util/paths.rb
-- lib/berkeley_library/util/stringios.rb
-- lib/berkeley_library/util/strings.rb
-- lib/berkeley_library/util/sys_exits.rb
-- lib/berkeley_library/util/times.rb
-- lib/berkeley_library/util/uris.rb
-- lib/berkeley_library/util/uris/appender.rb
-- lib/berkeley_library/util/uris/requester.rb
-- lib/berkeley_library/util/uris/validator.rb
 - rakelib/bundle.rake
 - rakelib/coverage.rake
 - rakelib/gem.rake
@@ -472,7 +477,7 @@ files:
 - spec/berkeley_library/tind/export/row_spec.rb
 - spec/berkeley_library/tind/export/table_spec.rb
 - spec/berkeley_library/tind/marc/xml_reader_spec.rb
-- spec/berkeley_library/util/arrays_spec.rb
+- spec/berkeley_library/tind/marc/xml_writer_spec.rb
 - spec/berkeley_library/util/ods/spreadsheet_spec.rb
 - spec/berkeley_library/util/ods/xml/content_doc_spec.rb
 - spec/berkeley_library/util/ods/xml/manifest/file_entry_spec.rb
@@ -482,14 +487,10 @@ files:
 - spec/berkeley_library/util/ods/xml/style/family_spec.rb
 - spec/berkeley_library/util/ods/xml/table/table_row_spec.rb
 - spec/berkeley_library/util/ods/xml/table/table_spec.rb
-- spec/berkeley_library/util/paths_spec.rb
-- spec/berkeley_library/util/stringios_spec.rb
-- spec/berkeley_library/util/strings_spec.rb
-- spec/berkeley_library/util/times_spec.rb
-- spec/berkeley_library/util/uris_spec.rb
 - spec/data/collection-names.txt
 - spec/data/collections.json
 - spec/data/disjoint-records.xml
+- spec/data/new-records.xml
 - spec/data/record-184453.xml
 - spec/data/record-184458.xml
 - spec/data/record-187888.xml
@@ -549,7 +550,7 @@ test_files:
 - spec/berkeley_library/tind/export/row_spec.rb
 - spec/berkeley_library/tind/export/table_spec.rb
 - spec/berkeley_library/tind/marc/xml_reader_spec.rb
-- spec/berkeley_library/util/arrays_spec.rb
+- spec/berkeley_library/tind/marc/xml_writer_spec.rb
 - spec/berkeley_library/util/ods/spreadsheet_spec.rb
 - spec/berkeley_library/util/ods/xml/content_doc_spec.rb
 - spec/berkeley_library/util/ods/xml/manifest/file_entry_spec.rb
@@ -559,14 +560,10 @@ test_files:
 - spec/berkeley_library/util/ods/xml/style/family_spec.rb
 - spec/berkeley_library/util/ods/xml/table/table_row_spec.rb
 - spec/berkeley_library/util/ods/xml/table/table_spec.rb
-- spec/berkeley_library/util/paths_spec.rb
-- spec/berkeley_library/util/stringios_spec.rb
-- spec/berkeley_library/util/strings_spec.rb
-- spec/berkeley_library/util/times_spec.rb
-- spec/berkeley_library/util/uris_spec.rb
 - spec/data/collection-names.txt
 - spec/data/collections.json
 - spec/data/disjoint-records.xml
+- spec/data/new-records.xml
 - spec/data/record-184453.xml
 - spec/data/record-184458.xml
 - spec/data/record-187888.xml

data/Jenkinsfile

@@ -1,18 +0,0 @@
-#!/usr/bin/env groovy
-
-dockerComposePipeline(
-    commands: [
-        'bundle exec rake coverage',
-        'bundle exec rake rubocop',
-        'bundle exec rake bundle:audit',
-        'bundle exec rake gem'
-    ],
-    artifacts: [
-        junit: 'artifacts/rspec/**/*.xml',
-        html : [
-            'Code Coverage': 'artifacts/rcov',
-            'RuboCop'      : 'artifacts/rubocop'
-        ],
-        raw  : ['artifacts/**/*.gem']
-    ]
-)

data/lib/berkeley_library/util/arrays.rb

@@ -1,178 +0,0 @@
-module BerkeleyLibrary
-  module Util
-    module Arrays
-      class << self
-        # Clients can chose to call class methods directly, or include the module
-        include Arrays
-      end
-
-      # Recursively checks whether the specified list contains, in the
-      # same order, all values in the other specified list (additional codes
-      # in between are fine)
-      #
-      # @param subset [Array] the values to look for
-      # @param superset [Array] the list of values to look in
-      # @return boolean True if all values were found, false otherwise
-      def ordered_superset?(superset:, subset:)
-        !find_indices(in_array: superset, for_array: subset).nil?
-      end
-
-      # Counts how many contiguous elements from the start of an
-      # sequence of values satisfy the given block.
-      #
-      # @overload count_while(arr:)
-      #   Returns an enumerator.
-      #   @param values [Enumerable] the values
-      #   @return [Enumerator] the enumerator.
-      # @overload count_while(arr:, &block)
-      #   Passes elements to the block until the block returns nil or false,
-      #   then stops iterating and returns the count of matching elements.
-      #   @param values [Enumerable] the values
-      #   @return [Integer] the count
-      def count_while(values:)
-        return to_enum(:count_while, values: values) unless block_given?
-
-        values.inject(0) do |count, x|
-          matched = yield x
-          break count unless matched
-
-          count + 1
-        end
-      end
-
-      # Given two lists, one of which is a superset of the other, with elements
-      # in the same order (but possibly with additional elements in the superset),
-      # returns an array the length of the subset, containing for each element in
-      # the subset the index of the corresponding element in the superset.
-      #
-      # @overload find_matching_indices(for_array:, in_array:)
-      #   For each value in `for_array`, finds the index of the first equal value
-      #   in `in_array` after the previously matched value.
-      #   @param in_array [Array] the list of values to look in
-      #   @param for_array [Array] the values to look for
-      #   @return [Array<Integer>, nil] the indices in `in_array` of each value in `for_array`,
-      #     or `nil` if not all values could be found
-      #
-      # @overload find_matching_indices(for_array:, in_array:)
-      #   For each value in `for_array`, finds the index of the first value
-      #   in `in_array` after the previously matched value that matches
-      #   the specified match function.
-      #   @param in_array [Array] the list of values to look in
-      #   @param for_array [Array] the values to look for
-      #   @yieldparam source [Object] the value to compare
-      #   @yieldparam target [Object] the value to compare against
-      #   @return [Array<Integer>, nil] the indices in `in_array` of each value in `for_array`,
-      #     or `nil` if not all values could be found
-      def find_indices(for_array:, in_array:, &block)
-        return find_indices_matching(for_array, in_array, &block) if block_given?
-
-        find_all_indices(for_array, in_array)
-      end
-
-      # Given a block or a value, finds the index of the first matching value
-      # at or after the specified start index.
-      #
-      # @overload find_index(value, in_array:, start_index:)
-      #   Finds the first index of the specified value.
-      #   @param value [Object] the value to find
-      #   @param in_array [Array] the array to search
-      #   @param start_index [Integer] the index to start with
-      #   @return [Integer, nil] the index, or `nil` if no value matches
-      # @overload find_index(&block)
-      #   Finds the index of the first value matching
-      #   the specified block.
-      #   @param in_array [Array] the array to search
-      #   @param start_index [Integer] the index to start with
-      #   @yieldreturn [Boolean] whether the element matches
-      #   @return [Integer, nil] the index, or `nil` if no value matches
-      # @overload find_index
-      #   @param in_array [Array] the array to search
-      #   @param start_index [Integer] the index to start with
-      #   @return [Enumerator] a new enumerator
-      def find_index(*args, in_array:, start_index: 0, &block)
-        raise ArgumentError, "wrong number of arguments (given #{value.length}, expected 0..1" if args.size > 1
-        return Enumerator.new { |y| find_index(in_array: in_array, start_index: start_index, &y) } if args.empty? && !block_given?
-        return unless (relative_index = in_array[start_index..].find_index(*args, &block))
-
-        relative_index + start_index
-      end
-
-      # Given an array of unique integers _a<sub>1</sub>_, returns a new array
-      # _a<sub>2</sub>_ in which the value at each index _i<sub>2</sub>_ is the
-      # index _i<sub>1</sub>_ at which that value was found in _a<sub>1</sub>_.
-      # E.g., given `[0, 2, 3]`, returns `[0, nil, 1, 2]`. The indices need
-      # not be in order but must be unique.
-      #
-      # @param arr [Array<Integer>, nil] the array to invert.
-      # @return [Array<Integer, nil>, nil] the inverted array, or nil if the input array is nil
-      # @raise TypeError if `arr` is not an array of integers
-      # @raise ArgumentError if `arr` contains duplicate values
-      def invert(arr)
-        return unless arr
-
-        # noinspection RubyNilAnalysis
-        Array.new(arr.size).tap do |inv|
-          arr.each_with_index do |v, i|
-            next inv[v] = i unless (prev_index = inv[v])
-
-            raise ArgumentError, "Duplicate value #{v} at index #{i} already found at #{prev_index}"
-          end
-        end
-      end
-
-      # Merges two arrays in an order-preserving manner.
-      # @param a1 [Array] the first array
-      # @param a2 [Array] the second array
-      # @return [Array] a merged array that is an ordered superset of both `a1` and `a2`
-      # @see Arrays#ordered_superset?
-      def merge(a1, a2)
-        return a1 if a2.empty?
-        return a2 if a1.empty?
-
-        shorter, longer = a1.size > a2.size ? [a2, a1] : [a1, a2]
-        do_merge(shorter, longer)
-      end
-
-      private
-
-      def do_merge(shorter, longer)
-        shorter.each_with_index do |v, ix_s|
-          next unless (ix_l = longer.find_index(v))
-
-          shorter_unmatched = shorter[0...ix_s]
-          longer_unmatched = longer[0...ix_l]
-          all_unmatched = sort_by_first_and_flatten(shorter_unmatched, longer_unmatched)
-          return (all_unmatched << v) + merge(shorter[ix_s + 1..], longer[ix_l + 1..])
-        end
-
-        sort_by_first_and_flatten(longer, shorter)
-      end
-
-      def sort_by_first_and_flatten(a1, a2)
-        return a1 if a2.empty?
-        return a2 if a1.empty?
-        return a2 + a1 if a1.first.respond_to?(:>) && a1.first > a2.first
-
-        a1 + a2
-      end
-
-      def find_all_indices(source, target)
-        source.each_with_object([]) do |src, target_indices|
-          target_offset = (target_indices.last&.+ 1) || 0
-          return nil unless (target_index = find_index(src, in_array: target, start_index: target_offset))
-
-          target_indices << target_index
-        end
-      end
-
-      def find_indices_matching(source, target)
-        source.each_with_object([]) do |src, target_indices|
-          target_offset = (target_indices.last&.+ 1) || 0
-          return nil unless (target_index = find_index(in_array: target, start_index: target_offset) { |tgt| yield src, tgt })
-
-          target_indices << target_index
-        end
-      end
-    end
-  end
-end

data/lib/berkeley_library/util/logging.rb

@@ -1 +0,0 @@
-require 'berkeley_library/logging'

data/lib/berkeley_library/util/paths.rb

@@ -1,111 +0,0 @@
-require 'berkeley_library/util/stringios'
-
-module BerkeleyLibrary
-  module Util
-    # This module, modeled on the {https://golang.org/pkg/path/ Go `path` package},
-    # provides utility routines for modifying paths separated by forward slashes,
-    # such as URL paths. For system-dependent file paths, use
-    # {https://ruby-doc.org/stdlib-2.7.0/libdoc/pathname/rdoc/Pathname.html `Pathname`}
-    # instead.
-    module Paths
-      include BerkeleyLibrary::Util::StringIOs
-
-      class << self
-        include Paths
-      end
-
-      # Returns the shortest path name equivalent to `path` by purely lexical
-      # processing by:
-      #
-      # 1. replacing runs of multiple `/` with a single `/`
-      # 2. eliminating all `.` (current directory) elements
-      # 3. eliminating all `<child>/..` in favor of directly
-      #    referencing the parent directory
-      # 4. replaing all `/..` at the beginning of the path
-      #    with a single leading `/`
-      #
-      # The returned path ends in a slash only if it is the root `/`.
-      # @see https://9p.io/sys/doc/lexnames.html Rob Pike, "Lexical File Names in Plan 9 or Getting Dot-Dot Right"
-      #
-      # @param path [String, nil] the path to clean
-      # @return [String, nil] the cleaned path, or `nil` for a nil path.
-      def clean(path)
-        return unless path
-        return '.' if ['', '.'].include?(path)
-
-        StringIO.new.tap do |out|
-          out << '/' if path[0] == '/'
-          dotdot = (r = out.size)
-          r, dotdot = process_next(r, dotdot, path, out) while r < path.size
-          out << '.' if out.pos == 0
-        end.string
-      end
-
-      # Joins any number of path elements into a single path, separating
-      # them with slashes, ignoring empty elements and passing the result
-      # to {Paths#clean}.
-      #
-      # @param elements [Array<String>] the elements to join
-      # @return [String] the joined path
-      def join(*elements)
-        elements = elements.reject { |e| [nil, ''].include?(e) }
-        joined_raw = elements.join('/')
-        return '' if joined_raw == ''
-
-        clean(joined_raw)
-      end
-
-      private
-
-      def process_next(r, dotdot, path, out)
-        # empty path element, or .
-        return r + 1, dotdot if empty_or_dot?(r, path)
-        # .. element: remove to last /
-        return handle_dotdot(r, dotdot, path, out) if dotdot?(r, path)
-
-        # real path element
-        [append_from(r, path, out), dotdot]
-      end
-
-      def handle_dotdot(r, dotdot, path, out)
-        if out.pos > dotdot
-          backtrack_to_dotdot(out, dotdot)
-        elsif path[0] != '/'
-          dotdot = append_dotdot(out)
-        end
-
-        [r + 2, dotdot]
-      end
-
-      def dotdot?(r, path)
-        path[r] == '.' && (r + 2 == path.size || path[r + 2] == '/')
-      end
-
-      def empty_or_dot?(r, path)
-        path[r] == '/' || (path[r] == '.' && (r + 1 == path.size || path[r + 1] == '/'))
-      end
-
-      def append_from(r, path, out)
-        out << '/' if (path[0] == '/' && out.pos != 1) || (path[0] != '/' && out.pos != 0)
-        while r < path.size && path[r] != '/'
-          out << path[r]
-          r += 1
-        end
-        r
-      end
-
-      def append_dotdot(out)
-        out << '/' if out.pos > 1
-        out << '..'
-        out.pos
-      end
-
-      def backtrack_to_dotdot(out, dotdot)
-        out.seek(-1, IO::SEEK_CUR)
-        out.seek(-1, IO::SEEK_CUR) while out.pos > dotdot && getbyte(out, out.pos) != 47 # '/' is ASCII 37
-        out.truncate(out.pos)
-      end
-
-    end
-  end
-end

data/lib/berkeley_library/util/stringios.rb

@@ -1,30 +0,0 @@
-require 'stringio'
-
-module BerkeleyLibrary
-  module Util
-    module StringIOs
-      class << self
-        include StringIOs
-      end
-
-      # Returns the byte (**not** character) at the specified byte index
-      # in the specified `StringIO`.
-      #
-      # @param s [StringIO] the StringIO to search in
-      # @param i [Integer] the byte index
-      # @return [Integer, nil] the byte, or nil if the byte index is invalid.
-      def getbyte(s, i)
-        return if i >= s.size
-        return if s.size + i < 0
-
-        pos_orig = s.pos
-        begin
-          s.seek(i >= 0 ? i : s.size + i)
-          s.getbyte
-        ensure
-          s.seek(pos_orig)
-        end
-      end
-    end
-  end
-end

data/lib/berkeley_library/util/strings.rb

@@ -1,42 +0,0 @@
-module BerkeleyLibrary
-  module Util
-    module Strings
-
-      ASCII_0 = '0'.ord
-      ASCII_9 = '9'.ord
-
-      def ascii_numeric?(s)
-        s.chars.all? do |c|
-          ord = c.ord
-          ord >= ASCII_0 && ord <= ASCII_9
-        end
-      end
-
-      # Locates the point at which two strings differ
-      #
-      # @return [Integer, nil] the index of the first character in either string
-      #   that differs from the other, or `nil` if the strings are identical,
-      #   or are not strings
-      def diff_index(s1, s2)
-        return unless string_like?(s1, s2)
-
-        shorter, longer = s1.size > s2.size ? [s2, s1] : [s1, s2]
-        shorter.chars.each_with_index do |c, i|
-          return i if c != longer[i]
-        end
-        shorter.length if shorter.length < longer.length # otherwise they're equal
-      end
-
-      class << self
-        include Strings
-      end
-
-      private
-
-      def string_like?(*strs)
-        strs.all? { |s| s.respond_to?(:chars) && s.respond_to?(:size) }
-      end
-
-    end
-  end
-end

data/lib/berkeley_library/util/sys_exits.rb

@@ -1,15 +0,0 @@
-module BerkeleyLibrary
-  module Util
-    # cf. BSD sysexits.h https://cgit.freebsd.org/src/tree/include/sysexits.h?h=releng/2.0
-    module SysExits
-      # successful termination
-      EX_OK = 0
-
-      # command line usage error
-      EX_USAGE = 64
-
-      # internal software error
-      EX_SOFTWARE = 70 # command line usage error
-    end
-  end
-end

data/lib/berkeley_library/util/times.rb

@@ -1,22 +0,0 @@
-require 'time'
-
-module BerkeleyLibrary
-  module Util
-    module Times
-      class << self
-        include Times
-      end
-
-      # @param time [Time, Date] the time
-      # @return the UTC time corresponding to `time`
-      def ensure_utc(time)
-        return unless time
-        return time if time.respond_to?(:utc?) && time.utc?
-        return time.getutc if time.respond_to?(:getutc)
-        return time.to_time.getutc if time.respond_to?(:to_time)
-
-        raise ArgumentError, "Not a date or time: #{time.inspect}"
-      end
-    end
-  end
-end