opal-rspec 0.8.0 → 1.0.0

data/diff-lcs/upstream/lib/diff/lcs/hunk.rb

@@ -0,0 +1,363 @@
+# frozen_string_literal: true
+
+require "diff/lcs/block"
+
+# A Hunk is a group of Blocks which overlap because of the context surrounding
+# each block. (So if we're not using context, every hunk will contain one
+# block.) Used in the diff program (bin/ldiff).
+class Diff::LCS::Hunk
+  OLD_DIFF_OP_ACTION = {"+" => "a", "-" => "d", "!" => "c"}.freeze # :nodoc:
+  ED_DIFF_OP_ACTION = {"+" => "a", "-" => "d", "!" => "c"}.freeze # :nodoc:
+
+  private_constant :OLD_DIFF_OP_ACTION, :ED_DIFF_OP_ACTION if respond_to?(:private_constant)
+
+  # Create a hunk using references to both the old and new data, as well as the
+  # piece of data.
+  def initialize(data_old, data_new, piece, flag_context, file_length_difference)
+    # At first, a hunk will have just one Block in it
+    @blocks = [Diff::LCS::Block.new(piece)]
+
+    if @blocks[0].remove.empty? && @blocks[0].insert.empty?
+      fail "Cannot build a hunk from #{piece.inspect}; has no add or remove actions"
+    end
+
+    if String.method_defined?(:encoding)
+      @preferred_data_encoding = data_old.fetch(0) { data_new.fetch(0, "") }.encoding
+    end
+
+    @data_old = data_old
+    @data_new = data_new
+
+    before = after = file_length_difference
+    after += @blocks[0].diff_size
+    @file_length_difference = after # The caller must get this manually
+    @max_diff_size = @blocks.map { |e| e.diff_size.abs }.max
+
+    # Save the start & end of each array. If the array doesn't exist (e.g.,
+    # we're only adding items in this block), then figure out the line number
+    # based on the line number of the other file and the current difference in
+    # file lengths.
+    if @blocks[0].remove.empty?
+      a1 = a2 = nil
+    else
+      a1 = @blocks[0].remove[0].position
+      a2 = @blocks[0].remove[-1].position
+    end
+
+    if @blocks[0].insert.empty?
+      b1 = b2 = nil
+    else
+      b1 = @blocks[0].insert[0].position
+      b2 = @blocks[0].insert[-1].position
+    end
+
+    @start_old = a1 || (b1 - before)
+    @start_new = b1 || (a1 + before)
+    @end_old = a2 || (b2 - after)
+    @end_new = b2 || (a2 + after)
+
+    self.flag_context = flag_context
+  end
+
+  attr_reader :blocks
+  attr_reader :start_old, :start_new
+  attr_reader :end_old, :end_new
+  attr_reader :file_length_difference
+
+  # Change the "start" and "end" fields to note that context should be added
+  # to this hunk.
+  attr_accessor :flag_context
+  undef :flag_context=
+  def flag_context=(context) # :nodoc: # standard:disable Lint/DuplicateMethods
+    return if context.nil? || context.zero?
+
+    add_start = context > @start_old ? @start_old : context
+
+    @start_old -= add_start
+    @start_new -= add_start
+
+    old_size = @data_old.size
+
+    add_end =
+      if (@end_old + context) > old_size
+        old_size - @end_old
+      else
+        context
+      end
+
+    add_end = @max_diff_size if add_end >= old_size
+
+    @end_old += add_end
+    @end_new += add_end
+  end
+
+  # Merges this hunk and the provided hunk together if they overlap. Returns
+  # a truthy value so that if there is no overlap, you can know the merge
+  # was skipped.
+  def merge(hunk)
+    return unless overlaps?(hunk)
+
+    @start_old = hunk.start_old
+    @start_new = hunk.start_new
+    blocks.unshift(*hunk.blocks)
+  end
+  alias_method :unshift, :merge
+
+  # Determines whether there is an overlap between this hunk and the
+  # provided hunk. This will be true if the difference between the two hunks
+  # start or end positions is within one position of each other.
+  def overlaps?(hunk)
+    hunk and (((@start_old - hunk.end_old) <= 1) or
+              ((@start_new - hunk.end_new) <= 1))
+  end
+
+  # Returns a diff string based on a format.
+  def diff(format, last = false)
+    case format
+    when :old
+      old_diff(last)
+    when :unified
+      unified_diff(last)
+    when :context
+      context_diff(last)
+    when :ed
+      self
+    when :reverse_ed, :ed_finish
+      ed_diff(format, last)
+    else
+      fail "Unknown diff format #{format}."
+    end
+  end
+
+  # Note that an old diff can't have any context. Therefore, we know that
+  # there's only one block in the hunk.
+  def old_diff(_last = false)
+    warn "Expecting only one block in an old diff hunk!" if @blocks.size > 1
+
+    block = @blocks[0]
+
+    # Calculate item number range. Old diff range is just like a context
+    # diff range, except the ranges are on one line with the action between
+    # them.
+    s = encode("#{context_range(:old, ",")}#{OLD_DIFF_OP_ACTION[block.op]}#{context_range(:new, ",")}\n")
+    # If removing anything, just print out all the remove lines in the hunk
+    # which is just all the remove lines in the block.
+    unless block.remove.empty?
+      @data_old[@start_old..@end_old].each { |e| s << encode("< ") + e.chomp + encode("\n") }
+    end
+
+    s << encode("---\n") if block.op == "!"
+
+    unless block.insert.empty?
+      @data_new[@start_new..@end_new].each { |e| s << encode("> ") + e.chomp + encode("\n") }
+    end
+
+    s
+  end
+  private :old_diff
+
+  def unified_diff(last = false)
+    # Calculate item number range.
+    s = encode("@@ -#{unified_range(:old, last)} +#{unified_range(:new, last)} @@\n")
+
+    # Outlist starts containing the hunk of the old file. Removing an item
+    # just means putting a '-' in front of it. Inserting an item requires
+    # getting it from the new file and splicing it in. We splice in
+    # +num_added+ items. Remove blocks use +num_added+ because splicing
+    # changed the length of outlist.
+    #
+    # We remove +num_removed+ items. Insert blocks use +num_removed+
+    # because their item numbers -- corresponding to positions in the NEW
+    # file -- don't take removed items into account.
+    lo, hi, num_added, num_removed = @start_old, @end_old, 0, 0
+
+    # standard:disable Performance/UnfreezeString
+    outlist = @data_old[lo..hi].map { |e| String.new("#{encode(" ")}#{e.chomp}") }
+    # standard:enable Performance/UnfreezeString
+
+    last_block = blocks[-1]
+
+    if last
+      old_missing_newline = missing_last_newline?(@data_old)
+      new_missing_newline = missing_last_newline?(@data_new)
+    end
+
+    @blocks.each do |block|
+      block.remove.each do |item|
+        op = item.action.to_s # -
+        offset = item.position - lo + num_added
+        outlist[offset][0, 1] = encode(op)
+        num_removed += 1
+      end
+
+      if last && block == last_block && old_missing_newline && !new_missing_newline
+        outlist << encode('\')
+        num_removed += 1
+      end
+
+      block.insert.each do |item|
+        op = item.action.to_s # +
+        offset = item.position - @start_new + num_removed
+        outlist[offset, 0] = encode(op) + @data_new[item.position].chomp
+        num_added += 1
+      end
+    end
+
+    outlist << encode('\') if last && new_missing_newline
+
+    s << outlist.join(encode("\n"))
+
+    s
+  end
+  private :unified_diff
+
+  def context_diff(last = false)
+    s = encode("***************\n")
+    s << encode("*** #{context_range(:old, ",", last)} ****\n")
+    r = context_range(:new, ",", last)
+
+    if last
+      old_missing_newline = missing_last_newline?(@data_old)
+      new_missing_newline = missing_last_newline?(@data_new)
+    end
+
+    # Print out file 1 part for each block in context diff format if there
+    # are any blocks that remove items
+    lo, hi = @start_old, @end_old
+    removes = @blocks.reject { |e| e.remove.empty? }
+
+    unless removes.empty?
+      # standard:disable Performance/UnfreezeString
+      outlist = @data_old[lo..hi].map { |e| String.new("#{encode("  ")}#{e.chomp}") }
+      # standard:enable Performance/UnfreezeString
+
+      last_block = removes[-1]
+
+      removes.each do |block|
+        block.remove.each do |item|
+          outlist[item.position - lo][0, 1] = encode(block.op) # - or !
+        end
+
+        if last && block == last_block && old_missing_newline
+          outlist << encode('\')
+        end
+      end
+
+      s << outlist.join(encode("\n")) << encode("\n")
+    end
+
+    s << encode("--- #{r} ----\n")
+    lo, hi = @start_new, @end_new
+    inserts = @blocks.reject { |e| e.insert.empty? }
+
+    unless inserts.empty?
+      # standard:disable Performance/UnfreezeString
+      outlist = @data_new[lo..hi].map { |e| String.new("#{encode("  ")}#{e.chomp}") }
+      # standard:enable Performance/UnfreezeString
+
+      last_block = inserts[-1]
+
+      inserts.each do |block|
+        block.insert.each do |item|
+          outlist[item.position - lo][0, 1] = encode(block.op) # + or !
+        end
+
+        if last && block == last_block && new_missing_newline
+          outlist << encode('\')
+        end
+      end
+      s << outlist.join(encode("\n"))
+    end
+
+    s
+  end
+  private :context_diff
+
+  def ed_diff(format, _last = false)
+    warn "Expecting only one block in an old diff hunk!" if @blocks.size > 1
+
+    s =
+      if format == :reverse_ed
+        encode("#{ED_DIFF_OP_ACTION[@blocks[0].op]}#{context_range(:old, ",")}\n")
+      else
+        encode("#{context_range(:old, " ")}#{ED_DIFF_OP_ACTION[@blocks[0].op]}\n")
+      end
+
+    unless @blocks[0].insert.empty?
+      @data_new[@start_new..@end_new].each do |e|
+        s << e.chomp + encode("\n")
+      end
+      s << encode(".\n")
+    end
+    s
+  end
+  private :ed_diff
+
+  # Generate a range of item numbers to print. Only print 1 number if the
+  # range has only one item in it. Otherwise, it's 'start,end'
+  def context_range(mode, op, last = false)
+    case mode
+    when :old
+      s, e = (@start_old + 1), (@end_old + 1)
+    when :new
+      s, e = (@start_new + 1), (@end_new + 1)
+    end
+
+    e -= 1 if last
+    e = 1 if e.zero?
+
+    s < e ? "#{s}#{op}#{e}" : e.to_s
+  end
+  private :context_range
+
+  # Generate a range of item numbers to print for unified diff. Print number
+  # where block starts, followed by number of lines in the block
+  # (don't print number of lines if it's 1)
+  def unified_range(mode, last)
+    case mode
+    when :old
+      s, e = (@start_old + 1), (@end_old + 1)
+    when :new
+      s, e = (@start_new + 1), (@end_new + 1)
+    end
+
+    length = e - s + (last ? 0 : 1)
+
+    first = length < 2 ? e : s # "strange, but correct"
+    length <= 1 ? first.to_s : "#{first},#{length}"
+  end
+  private :unified_range
+
+  def missing_last_newline?(data)
+    newline = encode("\n")
+
+    if data[-2]
+      data[-2].end_with?(newline) && !data[-1].end_with?(newline)
+    elsif data[-1]
+      !data[-1].end_with?(newline)
+    else
+      true
+    end
+  end
+
+  if String.method_defined?(:encoding)
+    def encode(literal, target_encoding = @preferred_data_encoding)
+      literal.encode target_encoding
+    end
+
+    def encode_as(string, *args)
+      args.map { |arg| arg.encode(string.encoding) }
+    end
+  else
+    def encode(literal, _target_encoding = nil)
+      literal
+    end
+
+    def encode_as(_string, *args)
+      args
+    end
+  end
+
+  private :encode
+  private :encode_as
+end

data/diff-lcs/upstream/lib/diff/lcs/internals.rb

@@ -0,0 +1,308 @@
+# frozen_string_literal: true
+
+class << Diff::LCS
+  def diff_traversal(method, seq1, seq2, callbacks, &block)
+    callbacks = callbacks_for(callbacks)
+    case method
+    when :diff
+      traverse_sequences(seq1, seq2, callbacks)
+    when :sdiff
+      traverse_balanced(seq1, seq2, callbacks)
+    end
+    callbacks.finish if callbacks.respond_to? :finish
+
+    if block
+      callbacks.diffs.map do |hunk|
+        if hunk.is_a? Array
+          hunk.map { |hunk_block| block[hunk_block] }
+        else
+          block[hunk]
+        end
+      end
+    else
+      callbacks.diffs
+    end
+  end
+  private :diff_traversal
+end
+
+module Diff::LCS::Internals # :nodoc:
+end
+
+class << Diff::LCS::Internals
+  # Compute the longest common subsequence between the sequenced
+  # Enumerables +a+ and +b+. The result is an array whose contents is such
+  # that
+  #
+  #     result = Diff::LCS::Internals.lcs(a, b)
+  #     result.each_with_index do |e, i|
+  #       assert_equal(a[i], b[e]) unless e.nil?
+  #     end
+  def lcs(a, b)
+    a_start = b_start = 0
+    a_finish = a.size - 1
+    b_finish = b.size - 1
+    vector = []
+
+    # Collect any common elements at the beginning...
+    while (a_start <= a_finish) && (b_start <= b_finish) && (a[a_start] == b[b_start])
+      vector[a_start] = b_start
+      a_start += 1
+      b_start += 1
+    end
+
+    # Now the end...
+    while (a_start <= a_finish) && (b_start <= b_finish) && (a[a_finish] == b[b_finish])
+      vector[a_finish] = b_finish
+      a_finish -= 1
+      b_finish -= 1
+    end
+
+    # Now, compute the equivalence classes of positions of elements.
+    # An explanation for how this works: https://codeforces.com/topic/92191
+    b_matches = position_hash(b, b_start..b_finish)
+
+    thresh = []
+    links = []
+    string = a.is_a?(String)
+
+    (a_start..a_finish).each do |i|
+      ai = string ? a[i, 1] : a[i]
+      bm = b_matches[ai]
+      k = nil
+      bm.reverse_each do |j|
+        # Although the threshold check is not mandatory for this to work,
+        # it may have an optimization purpose
+        # An attempt to remove it: https://github.com/halostatue/diff-lcs/pull/72
+        # Why it is reintroduced: https://github.com/halostatue/diff-lcs/issues/78
+        if k && (thresh[k] > j) && (thresh[k - 1] < j)
+          thresh[k] = j
+        else
+          k = replace_next_larger(thresh, j, k)
+        end
+        links[k] = [k.positive? ? links[k - 1] : nil, i, j] unless k.nil?
+      end
+    end
+
+    unless thresh.empty?
+      link = links[thresh.size - 1]
+      until link.nil?
+        vector[link[1]] = link[2]
+        link = link[0]
+      end
+    end
+
+    vector
+  end
+
+  # This method will analyze the provided patchset to provide a single-pass
+  # normalization (conversion of the array form of Diff::LCS::Change objects to
+  # the object form of same) and detection of whether the patchset represents
+  # changes to be made.
+  def analyze_patchset(patchset, depth = 0)
+    fail "Patchset too complex" if depth > 1
+
+    has_changes = false
+    new_patchset = []
+
+    # Format:
+    # [ # patchset
+    #   # hunk (change)
+    #   [ # hunk
+    #     # change
+    #   ]
+    # ]
+
+    patchset.each do |hunk|
+      case hunk
+      when Diff::LCS::Change
+        has_changes ||= !hunk.unchanged?
+        new_patchset << hunk
+      when Array
+        # Detect if the 'hunk' is actually an array-format change object.
+        if Diff::LCS::Change.valid_action? hunk[0]
+          hunk = Diff::LCS::Change.from_a(hunk)
+          has_changes ||= !hunk.unchanged?
+          new_patchset << hunk
+        else
+          with_changes, hunk = analyze_patchset(hunk, depth + 1)
+          has_changes ||= with_changes
+          new_patchset.concat(hunk)
+        end
+      else
+        fail ArgumentError, "Cannot normalise a hunk of class #{hunk.class}."
+      end
+    end
+
+    [has_changes, new_patchset]
+  end
+
+  # Examine the patchset and the source to see in which direction the
+  # patch should be applied.
+  #
+  # WARNING: By default, this examines the whole patch, so this could take
+  # some time. This also works better with Diff::LCS::ContextChange or
+  # Diff::LCS::Change as its source, as an array will cause the creation
+  # of one of the above.
+  def intuit_diff_direction(src, patchset, limit = nil)
+    string = src.is_a?(String)
+    count = left_match = left_miss = right_match = right_miss = 0
+
+    patchset.each do |change|
+      count += 1
+
+      case change
+      when Diff::LCS::ContextChange
+        le = string ? src[change.old_position, 1] : src[change.old_position]
+        re = string ? src[change.new_position, 1] : src[change.new_position]
+
+        case change.action
+        when "-" # Remove details from the old string
+          if le == change.old_element
+            left_match += 1
+          else
+            left_miss += 1
+          end
+        when "+"
+          if re == change.new_element
+            right_match += 1
+          else
+            right_miss += 1
+          end
+        when "="
+          left_miss += 1 if le != change.old_element
+          right_miss += 1 if re != change.new_element
+        when "!"
+          if le == change.old_element
+            left_match += 1
+          elsif re == change.new_element
+            right_match += 1
+          else
+            left_miss += 1
+            right_miss += 1
+          end
+        end
+      when Diff::LCS::Change
+        # With a simplistic change, we can't tell the difference between
+        # the left and right on '!' actions, so we ignore those. On '='
+        # actions, if there's a miss, we miss both left and right.
+        element = string ? src[change.position, 1] : src[change.position]
+
+        case change.action
+        when "-"
+          if element == change.element
+            left_match += 1
+          else
+            left_miss += 1
+          end
+        when "+"
+          if element == change.element
+            right_match += 1
+          else
+            right_miss += 1
+          end
+        when "="
+          if element != change.element
+            left_miss += 1
+            right_miss += 1
+          end
+        end
+      end
+
+      break if !limit.nil? && (count > limit)
+    end
+
+    no_left = left_match.zero? && left_miss.positive?
+    no_right = right_match.zero? && right_miss.positive?
+
+    case [no_left, no_right]
+    when [false, true]
+      :patch
+    when [true, false]
+      :unpatch
+    else
+      case left_match <=> right_match
+      when 1
+        if left_miss.zero?
+          :patch
+        else
+          :unpatch
+        end
+      when -1
+        if right_miss.zero?
+          :unpatch
+        else
+          :patch
+        end
+      else
+        fail "The provided patchset does not appear to apply to the provided \
+enumerable as either source or destination value."
+      end
+    end
+  end
+
+  # Find the place at which +value+ would normally be inserted into the
+  # Enumerable. If that place is already occupied by +value+, do nothing
+  # and return +nil+. If the place does not exist (i.e., it is off the end
+  # of the Enumerable), add it to the end. Otherwise, replace the element
+  # at that point with +value+. It is assumed that the Enumerable's values
+  # are numeric.
+  #
+  # This operation preserves the sort order.
+  def replace_next_larger(enum, value, last_index = nil)
+    # Off the end?
+    if enum.empty? || (value > enum[-1])
+      enum << value
+      return enum.size - 1
+    end
+
+    # Binary search for the insertion point
+    last_index ||= enum.size - 1
+    first_index = 0
+    while first_index <= last_index
+      i = (first_index + last_index) >> 1
+
+      found = enum[i]
+
+      return nil if value == found
+
+      if value > found
+        first_index = i + 1
+      else
+        last_index = i - 1
+      end
+    end
+
+    # The insertion point is in first_index; overwrite the next larger
+    # value.
+    enum[first_index] = value
+    first_index
+  end
+  private :replace_next_larger
+
+  # If +vector+ maps the matching elements of another collection onto this
+  # Enumerable, compute the inverse of +vector+ that maps this Enumerable
+  # onto the collection. (Currently unused.)
+  def inverse_vector(a, vector)
+    inverse = a.dup
+    (0...vector.size).each do |i|
+      inverse[vector[i]] = i unless vector[i].nil?
+    end
+    inverse
+  end
+  private :inverse_vector
+
+  # Returns a hash mapping each element of an Enumerable to the set of
+  # positions it occupies in the Enumerable, optionally restricted to the
+  # elements specified in the range of indexes specified by +interval+.
+  def position_hash(enum, interval)
+    string = enum.is_a?(String)
+    hash = Hash.new { |h, k| h[k] = [] }
+    interval.each do |i|
+      k = string ? enum[i, 1] : enum[i]
+      hash[k] << i
+    end
+    hash
+  end
+  private :position_hash
+end