X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=doc%2FString.html;fp=doc%2FString.html;h=f04ae9aa7771b3591944e48aa30427256ac4f35d;hb=074ce0bade4a2e3ab2210624ba598cd5edd0bec8;hp=e0921af7f555c9e878e958a8eb0df0b0bf313e72;hpb=066fa6953e201272b93df3b32f25fff2e18c4ec7;p=porter2stemmer.git diff --git a/doc/String.html b/doc/String.html index e0921af..f04ae9a 100644 --- a/doc/String.html +++ b/doc/String.html @@ -38,8 +38,8 @@
@@ -116,6 +116,15 @@
+
+

Files

+ +
+

Class Index @@ -150,45 +159,10 @@

String

-

The Porter 2 stemmer

-

-This is the Porter 2 stemming algorithm, as described at snowball.tartarus.org/algorithms/english/stemmer.html -The original paper is: -

-

-Porter, 1980, “An algorithm for suffix stripping”, -Program, Vol. 14, no. 3, pp 130-137 -

-

-Constants for the stemmer are in the Porter2 -module. -

-

-Procedures that implement the stemmer are added to the String class. -

-

-The stemmer algorithm is implemented in the porter2_stem procedure. -

-

Internationalisation

-

-There isn’t much, as this is a stemmer that only works for English. -

-

-The gb_english flag to the various procedures allows the stemmer -to treat the British English ’-ise’ the same as the American -English ’-ize’. -

-

Longest suffixes

-

-Several places in the algorithm require matching the longest suffix of a -word. The regexp engine in Ruby 1.9 seems to handle alterntives in regexps -by finding the alternative that matches at the first position in the -string. As we’re only talking about suffixes, that first match is -also the longest suffix. If the regexp engine changes, this behaviour may -change and break the stemmer. +

+Implementation of the Porter 2 stemmer. String#porter2_stem is the +main stemming procedure.

@@ -227,10 +201,10 @@ Returns true if the word ends with a short syllable 
-    # File lib/porter2.rb, line 87
-87:   def porter2_ends_with_short_syllable?
-88:     self =~ /#{Porter2::SHORT_SYLLABLE}$/ ? true : false
-89:   end
+ # File lib/porter2_implementation.rb, line 59 +59: def porter2_ends_with_short_syllable? +60: self =~ /#{Porter2::SHORT_SYLLABLE}$/ ? true : false +61: end
@@ -263,10 +237,10 @@ A word is short if it ends in a short syllable, and R1 is null 
-    # File lib/porter2.rb, line 93
-93:   def porter2_is_short_word?
-94:     self.porter2_ends_with_short_syllable? and self.porter2_r1.empty?
-95:   end
+ # File lib/porter2_implementation.rb, line 65 +65: def porter2_is_short_word? +66: self.porter2_ends_with_short_syllable? and self.porter2_r1.empty? +67: end
@@ -299,10 +273,10 @@ Turn all Y letters into y 
-     # File lib/porter2.rb, line 289
-289:   def porter2_postprocess
-290:     self.gsub(/Y/, 'y')
-291:   end
+ # File lib/porter2_implementation.rb, line 261 +261: def porter2_postprocess +262: self.gsub(/Y/, 'y') +263: end
@@ -343,19 +317,19 @@ doesn’t do that.) 
-    # File lib/porter2.rb, line 53
-53:   def porter2_preprocess    
-54:     w = self.dup
-55: 
-56:     # remove any initial apostrophe
-57:     w.gsub!(/^'*(.)/, '\1')
-58:     
-59:     # set initial y, or y after a vowel, to Y
-60:     w.gsub!(/^y/, "Y")
-61:     w.gsub!(/(#{Porter2::V})y/, '\1Y')
-62:     
-63:     w
-64:   end
+ # File lib/porter2_implementation.rb, line 25 +25: def porter2_preprocess +26: w = self.dup +27: +28: # remove any initial apostrophe +29: w.gsub!(/^'*(.)/, '\1') +30: +31: # set initial y, or y after a vowel, to Y +32: w.gsub!(/^y/, "Y") +33: w.gsub!(/(#{Porter2::V})y/, '\1Y') +34: +35: w +36: end
@@ -390,15 +364,15 @@ and ‘arsen-’ treated as special cases 
-    # File lib/porter2.rb, line 69
-69:   def porter2_r1
-70:     if self =~ /^(gener|commun|arsen)(?<r1>.*)/
-71:       Regexp.last_match(:r1)
-72:     else
-73:       self =~ /#{Porter2::V}#{Porter2::C}(?<r1>.*)$/
-74:       Regexp.last_match(:r1) || ""
-75:     end
-76:   end
+ # File lib/porter2_implementation.rb, line 41 +41: def porter2_r1 +42: if self =~ /^(gener|commun|arsen)(?<r1>.*)/ +43: Regexp.last_match(:r1) +44: else +45: self =~ /#{Porter2::V}#{Porter2::C}(?<r1>.*)$/ +46: Regexp.last_match(:r1) || "" +47: end +48: end
@@ -433,11 +407,11 @@ non-vowel after the first vowel 
-    # File lib/porter2.rb, line 80
-80:   def porter2_r2
-81:     self.porter2_r1 =~ /#{Porter2::V}#{Porter2::C}(?<r2>.*)$/
-82:     Regexp.last_match(:r2) || ""
-83:   end
+ # File lib/porter2_implementation.rb, line 52 +52: def porter2_r2 +53: self.porter2_r1 =~ /#{Porter2::V}#{Porter2::C}(?<r2>.*)$/ +54: Regexp.last_match(:r2) || "" +55: end
@@ -472,24 +446,24 @@ English. 
-     # File lib/porter2.rb, line 297
-297:   def porter2_stem(gb_english = false)
-298:     preword = self.porter2_tidy
-299:     return preword if preword.length <= 2
-300: 
-301:     word = preword.porter2_preprocess
-302:     
-303:     if Porter2::SPECIAL_CASES.has_key? word
-304:       Porter2::SPECIAL_CASES[word]
-305:     else
-306:       w1a = word.porter2_step0.porter2_step1a
-307:       if Porter2::STEP_1A_SPECIAL_CASES.include? w1a 
-308:         w1a
-309:       else
-310:         w1a.porter2_step1b(gb_english).porter2_step1c.porter2_step2(gb_english).porter2_step3(gb_english).porter2_step4(gb_english).porter2_step5.porter2_postprocess
-311:       end
-312:     end
-313:   end
+ # File lib/porter2_implementation.rb, line 269 +269: def porter2_stem(gb_english = false) +270: preword = self.porter2_tidy +271: return preword if preword.length <= 2 +272: +273: word = preword.porter2_preprocess +274: +275: if Porter2::SPECIAL_CASES.has_key? word +276: Porter2::SPECIAL_CASES[word] +277: else +278: w1a = word.porter2_step0.porter2_step1a +279: if Porter2::STEP_1A_SPECIAL_CASES.include? w1a +280: w1a +281: else +282: w1a.porter2_step1b(gb_english).porter2_step1c.porter2_step2(gb_english).porter2_step3(gb_english).porter2_step4(gb_english).porter2_step5.porter2_postprocess +283: end +284: end +285: end
@@ -528,41 +502,41 @@ output of each stage to STDOUT 
-     # File lib/porter2.rb, line 316
-316:   def porter2_stem_verbose(gb_english = false)
-317:     preword = self.porter2_tidy
-318:     puts "Preword: #{preword}"
-319:     return preword if preword.length <= 2
-320: 
-321:     word = preword.porter2_preprocess
-322:     puts "Preprocessed: #{word}"
-323:     
-324:     if Porter2::SPECIAL_CASES.has_key? word
-325:       puts "Returning #{word} as special case #{Porter2::SPECIAL_CASES[word]}"
-326:       Porter2::SPECIAL_CASES[word]
-327:     else
-328:       r1 = word.porter2_r1
-329:       r2 = word.porter2_r2
-330:       puts "R1 = #{r1}, R2 = #{r2}"
-331:     
-332:       w0 = word.porter2_step0 ; puts "After step 0:  #{w0} (R1 = #{w0.porter2_r1}, R2 = #{w0.porter2_r2})"
-333:       w1a = w0.porter2_step1a ; puts "After step 1a: #{w1a} (R1 = #{w1a.porter2_r1}, R2 = #{w1a.porter2_r2})"
-334:       
-335:       if Porter2::STEP_1A_SPECIAL_CASES.include? w1a
-336:         puts "Returning #{w1a} as 1a special case"
-337:         w1a
-338:       else
-339:         w1b = w1a.porter2_step1b(gb_english) ; puts "After step 1b: #{w1b} (R1 = #{w1b.porter2_r1}, R2 = #{w1b.porter2_r2})"
-340:         w1c = w1b.porter2_step1c ; puts "After step 1c: #{w1c} (R1 = #{w1c.porter2_r1}, R2 = #{w1c.porter2_r2})"
-341:         w2 = w1c.porter2_step2(gb_english) ; puts "After step 2:  #{w2} (R1 = #{w2.porter2_r1}, R2 = #{w2.porter2_r2})"
-342:         w3 = w2.porter2_step3(gb_english) ; puts "After step 3:  #{w3} (R1 = #{w3.porter2_r1}, R2 = #{w3.porter2_r2})"
-343:         w4 = w3.porter2_step4(gb_english) ; puts "After step 4:  #{w4} (R1 = #{w4.porter2_r1}, R2 = #{w4.porter2_r2})"
-344:         w5 = w4.porter2_step5 ; puts "After step 5:  #{w5}"
-345:         wpost = w5.porter2_postprocess ; puts "After postprocess: #{wpost}"
-346:         wpost
-347:       end
-348:     end
-349:   end
+ # File lib/porter2_implementation.rb, line 288 +288: def porter2_stem_verbose(gb_english = false) +289: preword = self.porter2_tidy +290: puts "Preword: #{preword}" +291: return preword if preword.length <= 2 +292: +293: word = preword.porter2_preprocess +294: puts "Preprocessed: #{word}" +295: +296: if Porter2::SPECIAL_CASES.has_key? word +297: puts "Returning #{word} as special case #{Porter2::SPECIAL_CASES[word]}" +298: Porter2::SPECIAL_CASES[word] +299: else +300: r1 = word.porter2_r1 +301: r2 = word.porter2_r2 +302: puts "R1 = #{r1}, R2 = #{r2}" +303: +304: w0 = word.porter2_step0 ; puts "After step 0: #{w0} (R1 = #{w0.porter2_r1}, R2 = #{w0.porter2_r2})" +305: w1a = w0.porter2_step1a ; puts "After step 1a: #{w1a} (R1 = #{w1a.porter2_r1}, R2 = #{w1a.porter2_r2})" +306: +307: if Porter2::STEP_1A_SPECIAL_CASES.include? w1a +308: puts "Returning #{w1a} as 1a special case" +309: w1a +310: else +311: w1b = w1a.porter2_step1b(gb_english) ; puts "After step 1b: #{w1b} (R1 = #{w1b.porter2_r1}, R2 = #{w1b.porter2_r2})" +312: w1c = w1b.porter2_step1c ; puts "After step 1c: #{w1c} (R1 = #{w1c.porter2_r1}, R2 = #{w1c.porter2_r2})" +313: w2 = w1c.porter2_step2(gb_english) ; puts "After step 2: #{w2} (R1 = #{w2.porter2_r1}, R2 = #{w2.porter2_r2})" +314: w3 = w2.porter2_step3(gb_english) ; puts "After step 3: #{w3} (R1 = #{w3.porter2_r1}, R2 = #{w3.porter2_r2})" +315: w4 = w3.porter2_step4(gb_english) ; puts "After step 4: #{w4} (R1 = #{w4.porter2_r1}, R2 = #{w4.porter2_r2})" +316: w5 = w4.porter2_step5 ; puts "After step 5: #{w5}" +317: wpost = w5.porter2_postprocess ; puts "After postprocess: #{wpost}" +318: wpost +319: end +320: end +321: end
@@ -612,10 +586,10 @@ and remove if found. 
-     # File lib/porter2.rb, line 103
-103:   def porter2_step0
-104:     self.sub!(/(.)('s'|'s|')$/, '\1') || self
-105:   end
+ # File lib/porter2_implementation.rb, line 75 +75: def porter2_step0 +76: self.sub!(/(.)('s'|'s|')$/, '\1') || self +77: end
@@ -668,26 +642,26 @@ do nothing 
-     # File lib/porter2.rb, line 113
-113:   def porter2_step1a
-114:     if self =~ /sses$/
-115:       self.sub(/sses$/, 'ss')
-116:     elsif self =~ /..(ied|ies)$/
-117:       self.sub(/(ied|ies)$/, 'i')
-118:     elsif self =~ /(ied|ies)$/
-119:       self.sub(/(ied|ies)$/, 'ie')
-120:     elsif self =~ /(us|ss)$/
-121:       self
-122:     elsif self =~ /s$/
-123:       if self =~ /(#{Porter2::V}.+)s$/
-124:         self.sub(/s$/, '') 
-125:       else
-126:         self
-127:       end
-128:     else
-129:       self
-130:     end
-131:   end
+ # File lib/porter2_implementation.rb, line 85 + 85: def porter2_step1a + 86: if self =~ /sses$/ + 87: self.sub(/sses$/, 'ss') + 88: elsif self =~ /..(ied|ies)$/ + 89: self.sub(/(ied|ies)$/, 'i') + 90: elsif self =~ /(ied|ies)$/ + 91: self.sub(/(ied|ies)$/, 'ie') + 92: elsif self =~ /(us|ss)$/ + 93: self + 94: elsif self =~ /s$/ + 95: if self =~ /(#{Porter2::V}.+)s$/ + 96: self.sub(/s$/, '') + 97: else + 98: self + 99: end +100: else +101: self +102: end +103: end
@@ -754,31 +728,31 @@ if the word is short: add e 
-     # File lib/porter2.rb, line 143
-143:   def porter2_step1b(gb_english = false)
-144:     if self =~ /(eed|eedly)$/
-145:       if self.porter2_r1 =~ /(eed|eedly)$/
-146:         self.sub(/(eed|eedly)$/, 'ee')
-147:       else
-148:         self
-149:       end
-150:     else
-151:       w = self.dup
-152:       if w =~ /#{Porter2::V}.*(ed|edly|ing|ingly)$/
-153:         w.sub!(/(ed|edly|ing|ingly)$/, '')
-154:         if w =~ /(at|lb|iz)$/
-155:           w += 'e' 
-156:         elsif w =~ /is$/ and gb_english
-157:           w += 'e' 
-158:         elsif w =~ /#{Porter2::Double}$/
-159:           w.chop!
-160:         elsif w.porter2_is_short_word?
-161:           w += 'e'
-162:         end
-163:       end
-164:       w
-165:     end
-166:   end
+ # File lib/porter2_implementation.rb, line 115 +115: def porter2_step1b(gb_english = false) +116: if self =~ /(eed|eedly)$/ +117: if self.porter2_r1 =~ /(eed|eedly)$/ +118: self.sub(/(eed|eedly)$/, 'ee') +119: else +120: self +121: end +122: else +123: w = self.dup +124: if w =~ /#{Porter2::V}.*(ed|edly|ing|ingly)$/ +125: w.sub!(/(ed|edly|ing|ingly)$/, '') +126: if w =~ /(at|lb|iz)$/ +127: w += 'e' +128: elsif w =~ /is$/ and gb_english +129: w += 'e' +130: elsif w =~ /#{Porter2::Double}$/ +131: w.chop! +132: elsif w.porter2_is_short_word? +133: w += 'e' +134: end +135: end +136: w +137: end +138: end
@@ -812,14 +786,14 @@ not the first letter of the word. 
-     # File lib/porter2.rb, line 171
-171:   def porter2_step1c
-172:     if self =~ /.+#{Porter2::C}(y|Y)$/
-173:       self.sub(/(y|Y)$/, 'i')
-174:     else
-175:       self
-176:     end
-177:   end
+ # File lib/porter2_implementation.rb, line 143 +143: def porter2_step1c +144: if self =~ /.+#{Porter2::C}(y|Y)$/ +145: self.sub(/(y|Y)$/, 'i') +146: else +147: self +148: end +149: end
@@ -863,29 +837,29 @@ cases in the procedure.) 
-     # File lib/porter2.rb, line 188
-188:   def porter2_step2(gb_english = false)
-189:     r1 = self.porter2_r1
-190:     s2m = Porter2::STEP_2_MAPS.dup
-191:     if gb_english
-192:       s2m["iser"] = "ise"
-193:       s2m["isation"] = "ise"
-194:     end
-195:     step_2_re = Regexp.union(s2m.keys.map {|r| Regexp.new(r + "$")})
-196:     if self =~ step_2_re
-197:       if r1 =~ /#{$&}$/
-198:         self.sub(/#{$&}$/, s2m[$&])
-199:       else
-200:         self
-201:       end
-202:     elsif r1 =~ /li$/ and self =~ /(#{Porter2::Valid_LI})li$/
-203:       self.sub(/li$/, '')
-204:     elsif r1 =~ /ogi$/ and self =~ /logi$/
-205:       self.sub(/ogi$/, 'og')
-206:     else
-207:       self
-208:     end
-209:   end
+ # File lib/porter2_implementation.rb, line 160 +160: def porter2_step2(gb_english = false) +161: r1 = self.porter2_r1 +162: s2m = Porter2::STEP_2_MAPS.dup +163: if gb_english +164: s2m["iser"] = "ise" +165: s2m["isation"] = "ise" +166: end +167: step_2_re = Regexp.union(s2m.keys.map {|r| Regexp.new(r + "$")}) +168: if self =~ step_2_re +169: if r1 =~ /#{$&}$/ +170: self.sub(/#{$&}$/, s2m[$&]) +171: else +172: self +173: end +174: elsif r1 =~ /li$/ and self =~ /(#{Porter2::Valid_LI})li$/ +175: self.sub(/li$/, '') +176: elsif r1 =~ /ogi$/ and self =~ /logi$/ +177: self.sub(/ogi$/, 'og') +178: else +179: self +180: end +181: end
@@ -927,24 +901,24 @@ with ‘al’, similarly to how ‘alize’ is treated.) 
-     # File lib/porter2.rb, line 220
-220:   def porter2_step3(gb_english = false)
-221:     if self =~ /ative$/ and self.porter2_r2 =~ /ative$/
-222:       self.sub(/ative$/, '')
-223:     else
-224:       s3m = Porter2::STEP_3_MAPS.dup
-225:       if gb_english
-226:         s3m["alise"] = "al"
-227:       end
-228:       step_3_re = Regexp.union(s3m.keys.map {|r| Regexp.new(r + "$")})
-229:       r1 = self.porter2_r1
-230:       if self =~ step_3_re and r1 =~ /#{$&}$/ 
-231:         self.sub(/#{$&}$/, s3m[$&])
-232:       else
-233:         self
-234:       end
-235:     end
-236:   end
+ # File lib/porter2_implementation.rb, line 192 +192: def porter2_step3(gb_english = false) +193: if self =~ /ative$/ and self.porter2_r2 =~ /ative$/ +194: self.sub(/ative$/, '') +195: else +196: s3m = Porter2::STEP_3_MAPS.dup +197: if gb_english +198: s3m["alise"] = "al" +199: end +200: step_3_re = Regexp.union(s3m.keys.map {|r| Regexp.new(r + "$")}) +201: r1 = self.porter2_r1 +202: if self =~ step_3_re and r1 =~ /#{$&}$/ +203: self.sub(/#{$&}$/, s3m[$&]) +204: else +205: self +206: end +207: end +208: end
@@ -986,28 +960,28 @@ found.) 
-     # File lib/porter2.rb, line 246
-246:   def porter2_step4(gb_english = false)
-247:     if self.porter2_r2 =~ /ion$/ and self =~ /(s|t)ion$/
-248:       self.sub(/ion$/, '')
-249:     else
-250:       s4m = Porter2::STEP_4_MAPS.dup
-251:       if gb_english
-252:         s4m["ise"] = ""
-253:       end
-254:       step_4_re = Regexp.union(s4m.keys.map {|r| Regexp.new(r + "$")})
-255:       r2 = self.porter2_r2
-256:       if self =~ step_4_re
-257:         if r2 =~ /#{$&}/
-258:           self.sub(/#{$&}$/, s4m[$&])
-259:         else
-260:           self
-261:         end
-262:       else
-263:         self
-264:       end
-265:     end
-266:   end
+ # File lib/porter2_implementation.rb, line 218 +218: def porter2_step4(gb_english = false) +219: if self.porter2_r2 =~ /ion$/ and self =~ /(s|t)ion$/ +220: self.sub(/ion$/, '') +221: else +222: s4m = Porter2::STEP_4_MAPS.dup +223: if gb_english +224: s4m["ise"] = "" +225: end +226: step_4_re = Regexp.union(s4m.keys.map {|r| Regexp.new(r + "$")}) +227: r2 = self.porter2_r2 +228: if self =~ step_4_re +229: if r2 =~ /#{$&}/ +230: self.sub(/#{$&}$/, s4m[$&]) +231: else +232: self +233: end +234: else +235: self +236: end +237: end +238: end
@@ -1051,21 +1025,21 @@ delete if in R2 and preceded by l 
-     # File lib/porter2.rb, line 272
-272:   def porter2_step5
-273:     if self =~ /ll$/ and self.porter2_r2 =~ /l$/
-274:       self.sub(/ll$/, 'l') 
-275:     elsif self =~ /e$/ and self.porter2_r2 =~ /e$/ 
-276:       self.sub(/e$/, '') 
-277:     else
-278:       r1 = self.porter2_r1
-279:       if self =~ /e$/ and r1 =~ /e$/ and not self =~ /#{Porter2::SHORT_SYLLABLE}e$/
-280:         self.sub(/e$/, '')
-281:       else
-282:         self
-283:       end
-284:     end
-285:   end
+ # File lib/porter2_implementation.rb, line 244 +244: def porter2_step5 +245: if self =~ /ll$/ and self.porter2_r2 =~ /l$/ +246: self.sub(/ll$/, 'l') +247: elsif self =~ /e$/ and self.porter2_r2 =~ /e$/ +248: self.sub(/e$/, '') +249: else +250: r1 = self.porter2_r1 +251: if self =~ /e$/ and r1 =~ /e$/ and not self =~ /#{Porter2::SHORT_SYLLABLE}e$/ +252: self.sub(/e$/, '') +253: else +254: self +255: end +256: end +257: end
@@ -1098,16 +1072,16 @@ Tidy up the word before we get down to the algorithm 
-    # File lib/porter2.rb, line 35
-35:   def porter2_tidy
-36:     preword = self.to_s.strip.downcase
-37:     
-38:     # map apostrophe-like characters to apostrophes
-39:     preword.gsub!(/‘/, "'")
-40:     preword.gsub!(/’/, "'")
-41: 
-42:     preword
-43:   end
+ # File lib/porter2_implementation.rb, line 7 + 7: def porter2_tidy + 8: preword = self.to_s.strip.downcase + 9: +10: # map apostrophe-like characters to apostrophes +11: preword.gsub!(/‘/, "'") +12: preword.gsub!(/’/, "'") +13: +14: preword +15: end