Class: ArxivSync::XMLParser
- Inherits:
-
Ox::Sax
- Object
- Ox::Sax
- ArxivSync::XMLParser
- Defined in:
- lib/arxivsync/parser.rb
Instance Attribute Summary collapse
-
#papers ⇒ Object
Returns the value of attribute papers.
Instance Method Summary collapse
- #clean(str) ⇒ Object
- #decode(string) ⇒ Object
- #end_element(name) ⇒ Object
-
#initialize ⇒ XMLParser
constructor
A new instance of XMLParser.
-
#latex_decode(str) ⇒ Object
Like LaTeX.decode but without the punctuation weirdness.
- #start_element(name, attributes = []) ⇒ Object
- #text(str) ⇒ Object
Constructor Details
#initialize ⇒ XMLParser
Returns a new instance of XMLParser.
31 32 33 |
# File 'lib/arxivsync/parser.rb', line 31 def initialize @entities = HTMLEntities.new end |
Instance Attribute Details
#papers ⇒ Object
Returns the value of attribute papers.
29 30 31 |
# File 'lib/arxivsync/parser.rb', line 29 def papers @papers end |
Instance Method Details
#clean(str) ⇒ Object
48 49 50 |
# File 'lib/arxivsync/parser.rb', line 48 def clean(str) str.gsub(/\s+/, ' ').strip end |
#decode(string) ⇒ Object
70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
# File 'lib/arxivsync/parser.rb', line 70 def decode(string) str = @entities.decode(string) # Process latex entities -- except inside equations decoded = "" equation = false segment = "" str.chars do |ch| if ch == '$' if !equation decoded << latex_decode(segment) segment = ch else decoded << segment + ch segment = "" end equation = !equation else segment << ch end end decoded << latex_decode(segment) end |
#end_element(name) ⇒ Object
156 157 158 159 160 161 162 163 164 |
# File 'lib/arxivsync/parser.rb', line 156 def end_element(name) case name when :version @model.versions.push(@version) when :metadata # End of a paper entry @papers.push(@model) end @el = nil end |
#latex_decode(str) ⇒ Object
Like LaTeX.decode but without the punctuation weirdness
53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
# File 'lib/arxivsync/parser.rb', line 53 def latex_decode(str) string = str.dup LaTeX::Decode::Base.normalize(string) LaTeX::Decode::Maths.decode!(string) LaTeX::Decode::Accents.decode!(string) LaTeX::Decode::Diacritics.decode!(string) #LaTeX::Decode::Punctuation.decode!(string) LaTeX::Decode::Symbols.decode!(string) LaTeX::Decode::Base.strip_braces(string) LaTeX.normalize_C(string) end |
#start_element(name, attributes = []) ⇒ Object
35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/arxivsync/parser.rb', line 35 def start_element(name, attributes=[]) @el = name case name when :ListRecords @papers = [] when :metadata @model = Paper.new @model.versions = [] when :version @version = Version.new end end |
#text(str) ⇒ Object
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
# File 'lib/arxivsync/parser.rb', line 96 def text(str) case @el # Necessary elements when :id @model.id = clean(str) when :submitter @model.submitter = decode(clean(str)) when :title @model.title = decode(clean(str)) when :authors # Author strings may contain strange metadata # Non-regex parsing to handle nested parens @model. = decode(clean(str)) depth = 0 no_parens = "" @model..chars do |ch| case ch when '(' depth += 1 when ')' depth -= 1 else no_parens << ch if depth == 0 end end @model. = no_parens.split(/,|:|;|\sand\s|\s?the\s/i) .map { |s| clean(s) } .reject { |s| s.empty? } when :categories @model.categories = clean(str).split(/\s/) when :abstract @model.abstract = decode(clean(str)) # Optional elements when :comments @model.comments = decode(clean(str)) when :"msc-class" @model.msc_class = clean(str) when :"report-no" @model.report_no = clean(str) when :"journal-ref" @model.journal_ref = clean(str) when :doi @model.doi = clean(str) when :proxy @model.proxy = clean(str) when :license @model.license = clean(str) # Versions when :date @version.date = Time.parse(clean(str)) when :size @version.size = clean(str) end end |