{"id":323,"date":"2016-04-21T16:30:36","date_gmt":"2016-04-21T14:30:36","guid":{"rendered":"http:\/\/yellingstone.info\/?p=323"},"modified":"2016-04-22T22:43:40","modified_gmt":"2016-04-22T20:43:40","slug":"%e6%94%b6%e9%9b%86%e4%b8%80%e7%af%87%e6%96%87%e7%ab%a0%e5%87%ba%e7%8e%b0%e7%9a%84%e6%89%80%e6%9c%89%e5%8a%a8%e8%af%8d%e8%af%8d%e5%b9%b2","status":"publish","type":"post","link":"http:\/\/yellingstone.info\/?p=323","title":{"rendered":"\u7edf\u8ba1\u6587\u7ae0\u91cc\u52a8\u8bcd\u8bcd\u5e72\u4f7f\u7528\u9891\u7387"},"content":{"rendered":"

\u60f3\u77e5\u9053\u54ea\u4e9b\u662f\u65af\u74e6\u5e0c\u91cc\u8bed\u4e2d\u51fa\u73b0\u9891\u7387\u6700\u9ad8\u7684\u52a8\u8bcd\u8bcd\u5e72\uff0c\u505a\u4e00\u4e2a\u6700\u5e38\u7528\u52a8\u8bcd\u8bcd\u5e72\u5217\u8868<\/strong>\u3002\u65b9\u6cd5\u662f\uff1a\u4e00\u4e2a\u8bcd\u4e00\u4e2a\u8bcd\u5730\u9605\u8bfb\u4e00\u7bc7\u6587\u7ae0\uff0c\u68c0\u6d4b\u8fd9\u4e2a\u8bcd\u662f\u5426\u662f\u52a8\u8bcd\u7684\u53d8\u5f62\uff08\u4e4b\u524d\u7684\u90e8\u5206\u662f\u5426\u7b26\u5408\u7279\u5b9a\u53d8\u5f62\u89c4\u5219\uff0c\u5728\u811a\u672c\u91cc\u9762\u88ab\u79f0\u4e3a pre-set\uff09\uff0c\u5982\u679c\u662f\u7684\u8bdd\u5c31\u653e\u8fdb\u4e00\u4e2a\u5b57\u5178\u91cc\u3002\u6700\u540e\u7edf\u8ba1\u4e00\u4e0b\u5b57\u5178\u91cc\u6700\u5e38\u51fa\u73b0\u7684\u90a3\u4e9b\u52a8\u8bcd\u8bcd\u5e72\u3002<\/p>\n

\u9700\u8981\u52a8\u8bcd\u8bcd\u5e72\u7684\u5217\u8868<\/a>\u3002<\/p>\n

[code language=”python”]
\n# prepare the pre-set
\n# affirmative
\npre1=[‘a’, ‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npre2=[‘ka’, ‘ki’, ‘li’, ‘me’, ‘mesha’, ‘na’, ‘ta’]
\npre3=[‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘mw’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npreS1=set()
\nfor p1 in pre1:
\n\tfor p2 in pre2:
\n\t\tpreS1.add(p1+p2)
\n\t\tfor p3 in pre3:
\n\t\t\tpreS1.add(p1+p2+p3)
\nfor p3 in pre3:
\n\tpreS1.add("hu")
\n\tpreS1.add("ku")
\n\tpreS1.add("hu"+p3)
\n\tpreS1.add("ku"+p3)
\n# negative present
\npre1=[‘ha’, ‘hai’, ‘hai’, ‘haki’, ‘haku’, ‘haku’, ‘hali’, ‘ham’, ‘hamu’, ‘hapa’, ‘hatu’, ‘hau’, ‘havi’, ‘hawa’, ‘hawa’, ‘haya’, ‘hazi’, ‘hu’, ‘si’]
\npre2=[‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘mw’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npreS2=set()
\nfor p1 in pre1:
\n\tpreS2.add(p1)
\n\tfor p2 in pre2:
\n\t\tpreS2.add(p1+p2)
\n# if subjuntive
\npre1=[‘a’, ‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npre2=[‘si’]
\npre3=[‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘mw’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npreS3=set()
\nfor p1 in pre1:
\n\tpreS3.add(p1)
\n\tfor p2 in pre2:
\n\t\tpreS3.add(p1+p2)
\n\t\tfor p3 in pre3:
\n\t\t\tpreS3.add(p1+p3)
\n\t\t\tpreS3.add(p1+p2+p3)<\/p>\n

# other negatives
\npre1=[‘ha’, ‘hai’, ‘hai’, ‘haki’, ‘haku’, ‘haku’, ‘hali’, ‘ham’, ‘hamu’, ‘hapa’, ‘hatu’, ‘hau’, ‘havi’, ‘hawa’, ‘hawa’, ‘haya’, ‘hazi’, ‘hu’, ‘si’]
\npre2=[‘ja’, ‘ku’, ‘ta’]
\npre3=[‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘mw’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’]
\npreS4=set()
\nfor p1 in pre1:
\n\tfor p2 in pre2:
\n\t\tpreS4.add(p1+p2)
\n\t\tfor p3 in pre3:
\n\t\t\tpreS4.add(p1+p2+p3)<\/p>\n

# prepare verb dictionary and the document<\/p>\n

verbD={}<\/p>\n

mydict=open("verb_stems.txt")
\ndictF=mydict.read()
\ndict=dictF.split()<\/p>\n

myfile=open("1.txt")
\nline=myfile.readline()
\n# junk words, which are most likely nouns or adverbs
\njunk=set([‘hakimu’, ‘kijamii’, ‘kitaalamu’, ‘mbali’, ‘mradi’, ‘mshauri’, ‘mstaafu’, ‘mujibu’, ‘taasisi’, ‘unyonge’, ‘upande’, ‘ushahidi’, ‘utalii’, ‘utamaduni’, ‘vipande’, ‘wachache’, ‘wajibu’, ‘washauri’, ‘washiriki’, ‘wataalamu’, ‘watalii’])
\n# processing the words<\/p>\n

def ongeza():
\n\tif l not in verbD.keys():
\n\t\tverbD[l]=1
\n\telif l in verbD.keys():
\n\t\tverbD[l]+=1
\n\tprint l+" in "+word<\/p>\n

while line:
\n\twords=line.split()
\n\tfor word in words:
\n\t\tstop=1
\n\t\tword=word.strip(".,!?").lower()
\n\t\tif word not in junk:
\n\t\t\tfor l in dict:
\n\t\t\t\t# if the verb stem located as the end of the word, in affirmative
\n\t\t\t\tif word.rfind(l)>0 and word.rfind(l)+len(l)==len(word) and word[:word.rfind(l)] in preS1 and stop:
\n\t\t\t\t\tongeza()
\n\t\t\t\t\tstop=0
\n\t\t\t\t# if the verb stem located as the end of the word, in negative present
\n\t\t\t\tlN=l[:-1]+l[-1].replace("a","i")
\n\t\t\t\tif word.rfind(lN)>0 and word.rfind(lN)+len(lN)==len(word) and word[:word.rfind(lN)] in preS2 and stop:
\n\t\t\t\t\tongeza()
\n\t\t\t\t\tstop=0
\n\t\t\t\t# if subjunctive
\n\t\t\t\tlS=l[:-1]+l[-1].replace("a","e")
\n\t\t\t\tif word.rfind(lS)>0 and word.rfind(lS)+len(lS)==len(word) and word[:word.rfind(lS)] in preS3 and stop:
\n\t\t\t\t\tongeza()
\n\t\t\t\t\tstop=0
\n\t\t\t\t# if the verb stem located as the end of the word, in negative
\n\t\t\t\tif word.rfind(l)>0 and word.rfind(l)+len(l)==len(word) and word[:word.rfind(l)] in preS4 and stop:
\n\t\t\t\t\tongeza()
\n\t\t\t\t\tstop=0
\n\tline=myfile.readline()
\n#print verbD
\nfor key in sorted(verbD.keys()):
\n\tprint key+": "+str(verbD[key])
\n[\/code]<\/p>\n

\u7ed3\u679c\uff08\u622a\u9009\uff09\uff1a
\n[code]
\nchoshwa: 3
\nchukua: 3
\ndaiwa: 2
\ndumu: 2
\neleza: 10
\nelezea: 6
\nendekeza: 1
\nendelea: 8
\nendeleza: 4
\nendesha: 2
\nepuka: 1
\nepusha: 1
\nfafanua: 1
\nfahamisha: 1
\nfahamu: 1
\nfaidika: 1
\nfanya: 7
\n[\/code]<\/p>\n","protected":false},"excerpt":{"rendered":"

\u60f3\u77e5\u9053\u54ea\u4e9b\u662f\u65af\u74e6\u5e0c\u91cc\u8bed\u4e2d\u51fa\u73b0\u9891\u7387\u6700\u9ad8\u7684\u52a8\u8bcd\u8bcd\u5e72\uff0c\u505a\u4e00\u4e2a\u6700\u5e38\u7528\u52a8\u8bcd\u8bcd\u5e72\u5217\u8868\u3002\u65b9\u6cd5\u662f\uff1a\u4e00\u4e2a\u8bcd\u4e00\u4e2a\u8bcd\u5730\u9605\u8bfb\u4e00\u7bc7\u6587\u7ae0\uff0c\u68c0\u6d4b\u8fd9\u4e2a\u8bcd\u662f\u5426\u662f\u52a8\u8bcd\u7684\u53d8\u5f62\uff08\u4e4b\u524d\u7684\u90e8\u5206\u662f\u5426\u7b26\u5408\u7279\u5b9a\u53d8\u5f62\u89c4\u5219\uff0c\u5728\u811a\u672c\u91cc\u9762\u88ab\u79f0\u4e3a pre-set\uff09\uff0c\u5982\u679c\u662f\u7684\u8bdd\u5c31\u653e\u8fdb\u4e00\u4e2a\u5b57\u5178\u91cc\u3002\u6700\u540e\u7edf\u8ba1\u4e00\u4e0b\u5b57\u5178\u91cc\u6700\u5e38\u51fa\u73b0\u7684\u90a3\u4e9b\u52a8\u8bcd\u8bcd\u5e72\u3002 \u9700\u8981\u52a8\u8bcd\u8bcd\u5e72\u7684\u5217\u8868\u3002 [code language=”python”] # prepare the pre-set # affirmative pre1=[‘a’, ‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’] pre2=[‘ka’, ‘ki’, ‘li’, ‘me’, ‘mesha’, ‘na’, ‘ta’] pre3=[‘i’, ‘ki’, ‘ku’, ‘li’, ‘m’, ‘mu’, ‘mw’, ‘ni’, ‘pa’, ‘tu’, ‘u’, ‘vi’, ‘wa’, ‘ya’, ‘zi’] preS1=set() for p1 in pre1: for p2 … →<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"_links":{"self":[{"href":"http:\/\/yellingstone.info\/index.php?rest_route=\/wp\/v2\/posts\/323"}],"collection":[{"href":"http:\/\/yellingstone.info\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/yellingstone.info\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/yellingstone.info\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/yellingstone.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=323"}],"version-history":[{"count":0,"href":"http:\/\/yellingstone.info\/index.php?rest_route=\/wp\/v2\/posts\/323\/revisions"}],"wp:attachment":[{"href":"http:\/\/yellingstone.info\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=323"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/yellingstone.info\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=323"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/yellingstone.info\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=323"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}