Load stopwords from a file

[ibnesayeed]

Supplying a long list of stopwords as an inline CLI argument can be tricky or even impossible. having an option to load it from a file would be great.

[ibnesayeed]

It looks like the default list of stopwords is hard-coded in a Python file. Perhaps it will be more flexible to extract it out as a text file and iterate over it during the loading process. This way, a custom list of stopwords can be provided the same way as the default one.

sumgram/sumgram/util.py

Lines 35 to 326 in 31434ea

	stopwordsDict = {
	"a": True,
	"about": True,
	"above": True,
	"across": True,
	"after": True,
	"afterwards": True,
	"again": True,
	"against": True,
	"all": True,
	"almost": True,
	"alone": True,
	"along": True,
	"already": True,
	"also": True,
	"although": True,
	"always": True,
	"am": True,
	"among": True,
	"amongst": True,
	"amoungst": True,
	"amount": True,
	"an": True,
	"and": True,
	"another": True,
	"any": True,
	"anyhow": True,
	"anyone": True,
	"anything": True,
	"anyway": True,
	"anywhere": True,
	"are": True,
	"around": True,
	"as": True,
	"at": True,
	"back": True,
	"be": True,
	"became": True,
	"because": True,
	"become": True,
	"becomes": True,
	"becoming": True,
	"been": True,
	"before": True,
	"beforehand": True,
	"behind": True,
	"being": True,
	"below": True,
	"beside": True,
	"besides": True,
	"between": True,
	"beyond": True,
	"both": True,
	"but": True,
	"by": True,
	"can": True,
	"can\'t": True,
	"cannot": True,
	"cant": True,
	"co": True,
	"could not": True,
	"could": True,
	"couldn\'t": True,
	"couldnt": True,
	"de": True,
	"describe": True,
	"detail": True,
	"did": True,
	"do": True,
	"does": True,
	"doing": True,
	"done": True,
	"due": True,
	"during": True,
	"e.g": True,
	"e.g.": True,
	"e.g.,": True,
	"each": True,
	"eg": True,
	"either": True,
	"else": True,
	"elsewhere": True,
	"enough": True,
	"etc": True,
	"etc.": True,
	"even though": True,
	"ever": True,
	"every": True,
	"everyone": True,
	"everything": True,
	"everywhere": True,
	"except": True,
	"for": True,
	"former": True,
	"formerly": True,
	"from": True,
	"further": True,
	"get": True,
	"go": True,
	"had": True,
	"has not": True,
	"has": True,
	"hasn\'t": True,
	"hasnt": True,
	"have": True,
	"having": True,
	"he": True,
	"hence": True,
	"her": True,
	"here": True,
	"hereafter": True,
	"hereby": True,
	"herein": True,
	"hereupon": True,
	"hers": True,
	"herself": True,
	"him": True,
	"himself": True,
	"his": True,
	"how": True,
	"however": True,
	"i": True,
	"ie": True,
	"i.e": True,
	"i.e.": True,
	"if": True,
	"in": True,
	"inc": True,
	"inc.": True,
	"indeed": True,
	"into": True,
	"is": True,
	"it": True,
	"its": True,
	"it's": True,
	"itself": True,
	"just": True,
	"keep": True,
	"latter": True,
	"latterly": True,
	"less": True,
	"made": True,
	"make": True,
	"may": True,
	"me": True,
	"meanwhile": True,
	"might": True,
	"mine": True,
	"more": True,
	"moreover": True,
	"most": True,
	"mostly": True,
	"move": True,
	"must": True,
	"my": True,
	"myself": True,
	"namely": True,
	"neither": True,
	"never": True,
	"nevertheless": True,
	"next": True,
	"no": True,
	"nobody": True,
	"none": True,
	"noone": True,
	"nor": True,
	"not": True,
	"nothing": True,
	"now": True,
	"nowhere": True,
	"of": True,
	"off": True,
	"often": True,
	"on": True,
	"once": True,
	"one": True,
	"only": True,
	"onto": True,
	"or": True,
	"other": True,
	"others": True,
	"otherwise": True,
	"our": True,
	"ours": True,
	"ourselves": True,
	"out": True,
	"over": True,
	"own": True,
	"part": True,
	"per": True,
	"perhaps": True,
	"please": True,
	"put": True,
	"rather": True,
	"re": True,
	"same": True,
	"see": True,
	"seem": True,
	"seemed": True,
	"seeming": True,
	"seems": True,
	"several": True,
	"she": True,
	"should": True,
	"show": True,
	"side": True,
	"since": True,
	"sincere": True,
	"so": True,
	"some": True,
	"somehow": True,
	"someone": True,
	"something": True,
	"sometime": True,
	"sometimes": True,
	"somewhere": True,
	"still": True,
	"such": True,
	"take": True,
	"than": True,
	"that": True,
	"the": True,
	"their": True,
	"theirs": True,
	"them": True,
	"themselves": True,
	"then": True,
	"thence": True,
	"there": True,
	"thereafter": True,
	"thereby": True,
	"therefore": True,
	"therein": True,
	"thereupon": True,
	"these": True,
	"they": True,
	"this": True,
	"those": True,
	"though": True,
	"through": True,
	"throughout": True,
	"thru": True,
	"thus": True,
	"to": True,
	"together": True,
	"too": True,
	"toward": True,
	"towards": True,
	"un": True,
	"until": True,
	"upon": True,
	"us": True,
	"very": True,
	"via": True,
	"was": True,
	"we": True,
	"well": True,
	"were": True,
	"what": True,
	"whatever": True,
	"when": True,
	"whence": True,
	"whenever": True,
	"where": True,
	"whereafter": True,
	"whereas": True,
	"whereby": True,
	"wherein": True,
	"whereupon": True,
	"wherever": True,
	"whether": True,
	"which": True,
	"while": True,
	"whither": True,
	"who": True,
	"whoever": True,
	"whole": True,
	"whom": True,
	"whose": True,
	"why": True,
	"will": True,
	"with": True,
	"within": True,
	"without": True,
	"would": True,
	"yet": True,
	"you": True,
	"your": True,
	"yours": True,
	"yourself": True,
	"yourselves": True
	}