function words map

mywords-go/artical/article.go

@@ -58,7 +58,7 @@ func ParseSourceUrl(sourceUrl string, expr string, proxyUrl *url.URL) (*Article,
 }
 
 // ParseVersion 如果article的文件的version不同，则进入文章页面会重新进行解析，但是不会更新解析时间。
-const ParseVersion = "0.0.6"
+const ParseVersion = "0.0.7"
 
 var regSentenceSplit = regexp.MustCompile(`[^ ][^ ][^ ][^ ]\. [A-Z“]`)
 
@@ -162,7 +162,7 @@ loopSentences:
 				continue
 			}
 			//word = strings.TrimPrefix(word, "’")
-			if _, ok := meaninglessMap[strings.ToLower(word)]; ok {
+			if _, ok := functionWordsMap[strings.ToLower(word)]; ok {
 				continue
 			}
 			if len(word) < minLen {
@@ -271,6 +271,3 @@ func getRespBody(www string, proxyUrl *url.URL) ([]byte, error) {
 	}
 	return body, nil
 }
-
-// define meaninglessMap
-var meaninglessMap = map[string]struct{}{}

mywords-go/artical/function_words.go

@@ -0,0 +1,190 @@
+package artical
+
+/*
+英语中的虚词（Function Words）包括几类词汇，这些词在句子中起着重要的结构或者语法作用，但它们通常不带有实际的内容信息。虚词包括了以下几种词类：
+
+1. 代词（Pronouns）: 用于代替名词的词，如 I, you, he, she, it, we, they, me, him, her, us, them.
+2. 冠词（Articles）: 用于修饰名词，标明特指或泛指，如 the, a, an.
+3. 介词（Prepositions）: 表示时间、位置、方向、原因等关系的词，如 in, on, at, to, for, with, by, over, under.
+4. 连词（Conjunctions）: 用于连接词、短语或从句，如 and, but, or, because, although, if, when, while.
+5. 助动词（Auxiliary Verbs）: 用于形成时态、语态或语气的动词，如 be, do, have, will, can, could, should, might.
+6. 情态动词（Modal Verbs）: 表示可能性、能力、许可等概念的特殊助动词，如 can, could, may, might, must, shall, should, will, would.
+7. 量词（Quantifiers）: 用于表示数量或者程度的词，如 some, any, many, much, few, little, enough.
+8. 限定词（Determiners）: 用来限定名词的词，常见的有 this, that, these, those, my, your, his, her, its, our, their.
+9. 疑问词（Interrogatives）: 用于构成疑问的词，如 who, what, where, when, why, how.
+10. 叹词（Interjections）: 用来表达情感的词，如 oh, ah, wow, ouch.
+
+虚词通常在句子中不承担主要的语义功能，但对于构建句子的语法结构是必不可少的。
+在一些自然语言处理或文本分析的应用中，虚词往往在某些情况下会被过滤掉，以便更集中地分析内容词（Content Words）所携带的信息。
+*/
+
+var functionWordsMap = map[string]struct{}{
+	"the":        {},
+	"a":          {},
+	"an":         {},
+	"they":       {},
+	"them":       {},
+	"their":      {},
+	"those":      {},
+	"these":      {},
+	"himself":    {},
+	"herself":    {},
+	"ourselves":  {},
+	"themselves": {},
+	"anybody":    {},
+	"everyone":   {},
+	"someone":    {},
+	"nobody":     {},
+	"other":      {},
+	"each":       {},
+	"either":     {},
+	"neither":    {},
+	"something":  {},
+	"anything":   {},
+	"nothing":    {},
+	"about":      {},
+	"above":      {},
+	"across":     {},
+	"after":      {},
+	"against":    {},
+	"along":      {},
+	"amid":       {},
+	"on":         {},
+	"over":       {},
+	"among":      {},
+	"around":     {},
+	"before":     {},
+	"behind":     {},
+	"below":      {},
+	"beneath":    {},
+	"beside":     {},
+	"between":    {},
+	"beyond":     {},
+	"during":     {},
+	"except":     {},
+	"inside":     {},
+	"outside":    {},
+	"through":    {},
+	"towards":    {},
+	"under":      {},
+	"without":    {},
+	"and":        {},
+	"but":        {},
+	"for":        {},
+	"nor":        {},
+	"or":         {},
+	"yet":        {},
+	"so":         {},
+	"because":    {},
+	"although":   {},
+	"unless":     {},
+	"however":    {},
+	"whereas":    {},
+	"whenever":   {},
+	"be":         {},
+	"have":       {},
+	"do":         {},
+	"can":        {},
+	"could":      {},
+	"may":        {},
+	"might":      {},
+	"must":       {},
+	"shall":      {},
+	"should":     {},
+	"will":       {},
+	"would":      {},
+	"ought":      {},
+	"some":       {},
+	"any":        {},
+	"many":       {},
+	"much":       {},
+	"few":        {},
+	"several":    {},
+	"plenty":     {},
+	"enough":     {},
+	"more":       {},
+	"most":       {},
+	"less":       {},
+	"least":      {},
+	"all":        {},
+	"both":       {},
+	"half":       {},
+	"this":       {},
+	"that":       {},
+	"such":       {},
+	"which":      {},
+	"what":       {},
+	"whose":      {},
+	"who":        {},
+	"whom":       {},
+	"where":      {},
+	"when":       {},
+	"why":        {},
+	"how":        {},
+	"wow":        {},
+	"gee":        {},
+	"gosh":       {},
+	"ugh":        {},
+	"yikes":      {},
+	"oops":       {},
+	"alas":       {},
+
+	"there":      {},
+	"itself":     {},
+	"myself":     {},
+	"yourself":   {},
+	"yourselves": {},
+
+	"everything": {},
+
+	"everybody": {},
+
+	"somebody": {},
+	"whoever":  {},
+	"whomever": {},
+
+	"throughout": {},
+	"toward":     {},
+	"within":     {},
+
+	"wherever": {},
+	"while":    {},
+	"since":    {},
+	"is":       {},
+	"am":       {},
+	"are":      {},
+	"was":      {},
+	"were":     {},
+	"being":    {},
+	"been":     {},
+	"has":      {},
+	"had":      {},
+	"having":   {},
+	"does":     {},
+	"did":      {},
+	"doing":    {},
+
+	"need": {},
+
+	"every": {},
+
+	"another": {},
+
+	"whatever":  {},
+	"whichever": {},
+
+	"hey":  {},
+	"ah":   {},
+	"oh":   {},
+	"ouch": {},
+	"hmm":  {},
+
+	"yay":    {},
+	"phew":   {},
+	"bummer": {},
+	"woah":   {},
+	"whoa":   {},
+	"hurray": {},
+	"er":     {},
+	"um":     {},
+}