style-check 0.15

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 57909f6c2ab0395b36cad6eaedd9e56c1fdd154a
+  data.tar.gz: 4f35cfb381ccd3e76681d57cf9270826b7787c06
+SHA512:
+  metadata.gz: 08802afdea2e3d15c8cb9b2aa2dc7b6514a063ae112fae90f00da8f4bc5b0d45e0c249843d5c328d10f3fda6194fe895f62b7e14dd2e6e48626d563fabd67b0b
+  data.tar.gz: a1422e3b139d6d7b8a451bc0fd0b8147b42f1d43fd943f55d1e88adf6c84c534035103fc4809e5f00276f712a529b2b6dfb3adf310826ab376aebd47fbb5c5e7

data/bin/style-check.rb

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+# this perhaps compounds the error a poor contant-filled
+# design, but by moving *all* the code to the gem/lib
+# location, the code can find the rules installed with the
+# gem.
+
+# it just feels so windows-dll like to do this.
+
+require 'style-check'
+

data/lib/rules/bad-words

@@ -0,0 +1,21 @@
+utilize              % phrase "use" http://www.bartleby.com/64/C003/0294.html
+utilizes             % phrase "uses" http://www.bartleby.com/64/C003/0294.html
+leverage             % phrase "use"
+abstraction          % phrase this is often used poorly?
+fashion              % phrase hrm.
+[dw]on't             % spelling do not or will not.
+behavioral           % spelling I'm convinced we don't use this word properly.
+we'll                % spelling we will
+we've                % spelling we have
+[^r][^c][^h] impact  % phrase "consequences", "effect", "result", though nsf likes "research impact"
+tackle               % phrase "tackle" (a problem) is wimpy for "solve" or a tired metaphor for "address a challenge".
+thusly               % phrase "thus" or "this way" or "like this" http://www.bartleby.com/64/C003/0282.html
+transpire            % phrase "happen" 
+so-called            % phrase can be abused; it's negative.
+necessitate          % phrase require.
+necessitated         % phrase required.
+necessitates         % phrase requires.
+loosing              % spelling you almost certainly mean "losing".  use "loosening" otherwise.
+aforementioned       % phrase too pretentious.
+important to         % phrase "valued by"?
+notion               % phrase avoid this weak phrase. (thanks brian bershad!)

data/lib/rules/barrass

@@ -0,0 +1,60 @@
+## I like this once in a while, for "goals" accomplish   % phrase do
+## A nice hint, but not a good rule. additional   % phrase extra, more
+anticipate   % phrase expect
+breakthrough % phrase discovery
+commence     % phrase begin
+conjecture   % phrase guess
+## I use this correctly. consider     % phrase think
+considerable % phrase much
+## I often use this in a technical sense. construct    % phrase build
+demonstrate  % phrase show
+encounter    % phrase meet
+endeavour    % phrase try
+excepting    % phrase except
+exhibit      % phrase show
+fabriacate   % phrase build
+firstly      % phrase first
+guidelines   % phrase guidance
+hypothesize  % phrase suggest
+indication   % phrase sign
+initiate     % phrase start
+modification % phrase change
+possess      % phrase have
+preventative % phrase preventive
+## often I use illustrations represents   % phrase is
+shortly      % phrase soon (though best to say when)
+subsequently % phrase later
+# sufficient   % phrase enough -- I often use sufficient technically.
+## I don't believe in this. upon         % phrase on
+utilisation  % phrase use
+## I don't believe in this. within       % phrase in
+virtually    % phrase almost
+currently    % phrase now
+absolutely essential           % phrase essential
+an actual investigation        % phrase an investigation
+almost unique                  % phrase rare
+completely surrounded          % phrase surrounded
+conclusive proof               % phrase proof
+an essential condition         % phrase a condition
+hard evidence                  % phrase evidence
+they are in fact               % phrase they are
+few in number                  % phrase few
+a positive identification      % phrase an identification
+quite obvious                  % phrase obvious
+real problems                  % phrase problems
+streamlined in appearance      % phrase streamlined
+quite unique                   % phrase unique
+every individual one           % phrase every one
+the reason for this is because % phrase because
+reason why                     % phrase reason -awu
+reverted back                  % phrase reverted
+related to each other          % phrase related
+each individual person         % phrase each person
+in actual fact                 % phrase in fact
+a specific example             % phrase an example
+an integral part               % phrase a part
+different varieties            % phrase varieties
+grouped together               % phrase grouped
+percolate down                 % phrase percolate
+eradicate completely           % phrase eradicate
+give positive encouragement    % phrase encourage

data/lib/rules/cliche

@@ -0,0 +1,5 @@
+dig deeper % phrase cliche
+attack these problems % phrase bobby dislikes
+crack these problems % phrase bobby dislikes
+attack this problem % phrase bobby dislikes
+crack this problem % phrase bobby dislikes

data/lib/rules/common-typos

@@ -0,0 +1,58 @@
+a the                % phrase double article
+ pt                  % syntax ? I guess avoid straggling pt's that escape tex?
+[ ],                 % syntax whitespace before comma seems wrong.
+''[\.,]              % syntax end quotes go outside punctuation like . and ,
+Figure Figure        % phrase pizza pizza.
+[ ]-[ ]              % syntax a hyphen surrounded by space should probably be an emdash '---'
+[0-9]-[0-9]          % syntax use an endash '--' for ranges
+[0-9]ms              % syntax put a space between the number and the unit.
+[^egs]\. [a-z]       % syntax a period usually ends a sentence, and sentences should start with a capital; doesn't apply for i.e., 
+\.  [a-z]            % syntax a period usually ends a sentence, and sentences should start with a capital; "i.e." should have a comma following.
+[a-z]\.\.            % syntax double period is rarely right, use \ldots for ellipsis
+[^\\]"               % syntax use fancy quotes
+\beg\.               % syntax should be e.g. as in "examples given"
+from to\b            % phrase haven't used this properly.
+help help            % phrase double word, that probably means the author paniced
+of of                % phrase apparent double word.
+the affect           % phrase should probably be 'the effect'
+the the              % phrase apparent double word.
+there too few        % phrase there are too few?
+was not was          % phrase pretty much a joke if this gets matched.
+we we                % phrase it would be oi oi in french, I guess.
+with on              % phrase probably wrong.
+with with            % phrase apparent double word.
+[\n ]--[\n ]         % syntax that's an en-dash, you want an em-dash: "---"
+my my                % phrase unlikely that's what you want, at least without a comma. (doesn't work across newlines)
+>From                % syntax be careful when you email .tex files.  I've seen this slip through into submissions.
+e\.t\.c\.            % syntax it's et cetera; use etc.
+such as like         % phrase pick one
+<<<<<<< .            % syntax CVS conflict!
+=======              % syntax CVS conflict!
+>>>>>>> [0-9]        % syntax CVS conflict!
+[;:]''               % syntax close quotes before (semi-)colons, but after commas and periods
+e\.g\.[\n ]          % syntax should be followed with a comma, as e.g. can be read as "for example" (thanks JZ!)
+i\.e\.[\n ]          % syntax should be followed with a comma, as i.e. can be read as "that is" (thanks JZ!)
+[ ]\.[\n ]           % syntax stray period?
+further more         % phrase one word: furthermore
+safe guard           % phrase one word: safeguard
+that be              % phrase mistake.
+can not              % phrase cannot
+only only            % phrase double word
+is is                % phrase double word.
+they shows           % phrase argh, mistake.
+less that than       % phrase typo damage
+from from            % phrase double word score
+in in                % phrase "in" (common mistake)
+not not              % phrase argh.
+it it                % phrase argh.
+to illicit           % phrase "to elicit" -- illicit is always an adjective.
+c\.f\.               % phrase actually, it's cf., and you'd like cf.\ (backslash space)
+this lead to         % phrase "led to" if past tense, "leads to" if present.
+on on                % phrase double word.
+has is               % phrase choose
+description their    % phrase saw this, clearly wrong.
+including:  % syntax I prefer no colon after including, which already says a list is coming.
+[a-z]\([A-Z]  % syntax put a space before parens, even when introducing acronyms.
+without and without % phrase saw this.
+can be result       % phrase saw this typo.
+

data/lib/rules/day-gastel

@@ -0,0 +1,214 @@
+a considerable amount of % phrase "much"
+a considerable number of % phrase "many"
+a decreased amount of % phrase "less"
+a decreased number of % phrase "fewer"
+a great deal of % phrase "much"
+a majority of % phrase "most", though 'a majority of' implies more than 50% while most implies significantly more.
+a number of % phrase "many" or "some"
+a situation in which % phrase "when"
+a small number of % phrase "a few" 
+absolutely essential % phrase "essential"
+accounted for by the fact % phrase "because"
+adjacent to % phrase "near" or "next to"
+along the lines of  % phrase "like"
+an adequate amount of % phrase "enough"
+an example of this is the fact that % phrase "for example"
+an order of magnitude faster % phrase "10 times as fast"
+apprise % phrase "inform"
+are of the same opinion % phrase "agree"
+as a consequence of % phrase "because"
+as a matter of fact % phrase "in fact" or leave out
+as a result of % phrase "because"
+as is the case % phrase "as happens"
+as of this date % phrase "today"
+as to % phrase "about" or leave out
+at a rapid rate % phrase "rapidly" or "fast"
+at an earlier date  % phrase "soon"
+at no time % phrase "never"
+at present % phrase "now"
+at some future time % phrase "later" or "sometime"
+at the conclusion of % phrase "after"
+at the present time % phrase "now"
+at this point in time % phrase "now"
+based on the fact that % phrase "because"
+because of the fact that % phrase "because"
+by means of % phrase "by" or "with
+causal factor % phrase "cause"
+cognizant of % phrase "aware of"
+completely full % phrase "full"
+consensus of opinion % phrase "consensus"
+considerable amount of % phrase "much"
+contingent upon % phrase "dependent on"
+count the number of  % phrase "count"
+definitely proved % phrase "proved"
+despite the fact that % phrase "although"
+due to the fact that % phrase "because"
+during the course of % phrase "during" or "while"
+during the time that % phrase "while"
+effectuate % phrase "cause"
+elucidate % phrase "explain"
+employ % phrase "use"
+enclosed herewith % phrase "enclosed"
+end result % phrase "result"
+endeavor % phrase "try"
+entirely eliminate % phrase "eliminate"
+eventuate % phrase "happen"
+fabricate % phrase "make"
+facilitate % phrase "help"
+fatal outcome % phrase "death"
+fellow colleague % phrase "colleague"
+fewer in number % phrase "fewer"
+finalize % phrase "end"
+first of all % phrase "first"
+for the purpose of  % phrase "for"
+for the reason that % phrase "because"
+from the point of view of % phrase "for"
+future plans % phrase "plans"
+give an account of % phrase "describe"
+give rise to % phrase "cause"
+has been engaged in a study of  % phrase "has studied"
+has the capability of % phrase "can"
+has the potential to % phrase "can" or "may"
+have the appearance of % phrase "look like" or "resemble"
+having regard to % phrase "about"
+immune serum % phrase "antiserum"
+important essentials % phrase "essentials"
+in a number of cases % phrase "sometimes"
+in a position to % phrase "able to"
+in a satisfactory manner % phrase "satisfactorily"
+in a situation in which % phrase "when"
+in a very real sense % phrase "in a sense" or leave out
+in almost all instances % phrase "nearly always"
+in case % phrase "if"
+in close proximity to % phrase "close" or "near"
+in connection with % phrase "about" or "concerning"
+in light of the fact that % phrase "because"
+in many cases % phrase "often"
+in most cases  % phrase "usually"
+in my opinion it is not an unjustifiable assumption that  % phrase "I think"
+in only a small number of cases  % phrase "rarely"
+in order to % phrase "to"
+in relation to % phrase "toward" or "to"
+in respect to % phrase "about"
+in some cases % phrase "sometimes"
+in terms of % phrase "about"
+in the absence of  % phrase "without"
+in the event that % phrase "if"
+in the most effective manner % phrase "most effectively"
+in the not too distant future % phrase "soon"
+in the not-too-distant future % phrase "soon"
+in the possession of % phrase "has" or "have"
+in this day and age % phrase "today"
+in view of the fact that % phrase "because"
+inasmuch as % phrase "for" or "as"
+in as much as  % phrase "for" or "as"
+incline to the view % phrase "think"
+inclined to the view % phrase "thought"
+initiate % phrase "begin" or "start"
+is defined as  % phrase "is"
+is desirous of % phrase "wants"
+is detrimental to % phrase "harms"
+is similar to % phrase "resembles"
+it has been reported by  % phrase "___ reported"
+it has long been known that % phrase "I haven't looked up the reference"
+it is apparent that % phrase "apparently" or "clearly"
+it is believed that % phrase "I think" (or say who thinks)
+it is clear that % phrase "clearly"
+it is clear that much additional work will be required % phrase "I don't understand it"
+it is evident that % phrase probably not needed just say what happened
+it is generally believed % phrase "many think"
+it is my understanding that % phrase "I understand that"
+it is of interest to note that % phrase leave out
+it is often the case that % phrase "often"
+it is suggested that % phrase "I think"
+it is worth pointing out in this context  % phrase omit
+it may be that % phrase "I think" or "perhaps"
+it may, however, be noted that % phrase "but"
+it should be noted that  % phrase omit
+it was observed in the course of the experiments that % phrase "we observed"
+join together % phrase "join"
+lacked the ability to % phrase "could not"
+large in size % phrase "large"
+let me make one thing perfectly clear % phrase A snow job is coming...
+majority of % phrase "most"
+make reference to % phrase "refer to"
+militate against % phrase "prohibit"
+more often than not % phrase "usually"
+needless to say % phrase (leave out, and consider leaving out what follows it)
+new initiatives % phrase "initiatives"
+no later than % phrase "by"
+of an efficient nature % phrase "efficient"
+of great theoretical and practical importance % phrase "useful"
+of long standing % phrase "old"
+of the opinion that % phrase "think that"
+on a daily basis % phrase "daily"
+on account of  % phrase "because"
+on behalf of  % phrase "for"
+on no occasion % phrase "never"
+on the basis of % phrase "by"
+on the grounds that % phrase "because"
+on the part of % phrase "by" or "among" or "for"
+on those occasions in which % phrase "when"
+our attention has been called to the fact that % phrase "we belatedly discovered"
+owing to the fact that  % phrase "because"
+perform % phrase "do"
+place a major emphasis on % phrase "stress" or "emphasize"
+pooled together % phrase "pooled"
+presents a picture similar to % phrase "resembles"
+previous to % phrase "before"
+prior to % phrase "before"
+determinations were performed % phrase "were determined"
+quantify % phrase "measure"
+quite a large quantity of  % phrase "much"
+quite unique % phrase "unique"
+rather interesting % phrase "interesting'
+red in color % phrase "red"
+referred to as  % phrase "called"
+regardless of the fact that % phrase "even though"
+relative to % phrase "about"
+resultant effect % phrase "result"
+root cause % phrase "cause"
+serious crisis % phrase "crisis"
+should prove the case that % phrase "if"
+smaller in size % phrase "smaller"
+so as to  % phrase "to"
+subject matter % phrase "subject"
+subsequent to % phrase "after"
+sufficient % phrase "enough"
+take into consideration % phrase "consider"
+terminate % phrase "end"
+the fact of the matter is that  % phrase (leave out)
+the field of % phrase just say the field name "chemistry"
+the great majority of  % phrase "most" or "almost all"
+the opinion is advanced that  % phrase "I think"
+the predominate number of % phrase "most"
+the question as to whether  % phrase "whether"
+the reason is because % phrase "because"
+the vast majority of % phrase "most" or "almost all"
+there is a reason to believe % phrase "I think"
+they are the investigators % phrase "they"
+this result would seem to indicate % phrase "the result indicates"
+results seem to indicate % phrase "the results indicate"
+result seems to indicate % phrase "the result indicates"
+through the use of % phrase "by" or "with"
+to the fullest possible extent % phrase "fully"
+transpire % phrase "happen"
+ultimate % phrase "last"
+unanimity of opinion % phrase "agreement"
+until such time % phrase "until"
+utilization % phrase "use"
+utilize % phrase "use"
+very unique % phrase "unique"
+was of the opinion % phrase "believed"
+ways and means % phrase "ways" or "means" but not both
+we have insufficient knowledge % phrase "we do not know"
+we wish to thank % phrase "we thank"
+what is the explanation of % phrase "why"
+whether or not to % phrase "whether to"
+with a view to % phrase "to"
+with reference to % phrase "about" (or leave out)
+with regard to % phrase "concerning" or "about" (or leave out)
+with respect to  % phrase "about
+with the exception of  % phrase "except"
+with the result that % phrase "so that"
+within the realm of possibility % phrase "possible"

data/lib/rules/foolish-phrases

@@ -0,0 +1,18 @@
+(quite|more|very|most) unique    % phrase unique is.
+(quite|more|very|most) abstract  % phrase abstract is.
+tangible view                    % phrase mix that metaphor some more.
+for e\.g\.                       % phrase e.g. includes "for".
+begs the question                % phrase unless you're very clever: "raises the question": http://alt-usage-english.org/excerpts/fxbegthe.html
+high rate of speed               % phrase local news-speak.
+especially necessary             % phrase 'especially important', necessary may be an absolute like unique.
+how will it effect % phrase you likely meant "affect"
+how it will effect % phrase you likely meant "affect"
+insure proper performance % phrase "ensure"
+especially true                  % phrase 'especially important', true may be an absolute like unique.
+to affect change                 % phrase "effect" change;  I read this on a poster.
+higher results                   % phrase maybe higher performance or higher values.
+is more general then the         % phrase probably "than"
+upper bounding                   % phrase "limiting" or "setting an upper bound on"
+in principal                     % phrase likely, "in principle"
+literally like                   % phrase literally means no simile.  
+design principal  % phrase likely, "design principle" 

data/lib/rules/latex-checking

@@ -0,0 +1,27 @@
+\{\\em [^\}]*[^\}\/]\}[:]    % syntax use \emph{} or explicit italic correction {\em foo\/}
+\{\\em [^\}]*[:\.,]\}        % syntax punctuation at the edges of italic text is not italicized
+[A-Z]{2,10}\.[ ]*[\n ][ ]*[A-Z]  % syntax intersentence spacing should be used if a sentence ends with an acronym: "FOO\\@."
+\\etal[^{]                   % syntax it's good practice to use \etal{} to avoid bad spacing
+\\caption\[[^\]]*[^\.]\]     % syntax short caption should end with a period.
+\\caption\[.*CCDF.*\]        % syntax short caption should not include graph type.
+\\caption\[.*CDF.*\]         % syntax short caption should not include graph type.
+\\caption\[.{0,25}\]         % syntax short caption should not be too short.
+[ ]---[ ]                    % syntax the em-dash should be right up against the words.
+[ \n]---[ \n]                % syntax the em-dash should be right up against the words.
+^---[ \n]                    % syntax the em-dash should be right up against the words.
+[ \n]---$                    % syntax the em-dash should be right up against the words.
+[ \n]--[ \n]                 % syntax the en-dash should be between numbers.
+^--[ \n]                     % syntax the en-dash should be between numbers.
+[ \n]--$                     % syntax the en-dash should be rbetween numbers.
+,[~ ]\\etal                  % syntax no comma before etal (unless Smith, Martinez, \etal)
+\\etal\{\}'s                 % syntax eew.
+\\(sub)?section\{[A-Z][^}]*[ ][a-z]{5,40}[^}]*\} % syntax subsection headers should be initial capped.
+\\(sub)?section\{[A-Z][^}]*[^:][ ]{1,}(With|A|An|Is|And|For|To|The)[ ][^}]*\} % syntax some words needn't be capitalized
+[ ]\\footnote                % syntax no space before footnote.  
+,,                           % syntax double comma is unlikely to be intentional.
+cf\.[^\\]                     % phrase cf. should get an escaped space "\ "
+[a-z]''[\.]                     % syntax close quotes outside the period. (doesn't seem to work.)
+[<>]  % syntax a less than or greater than outside math mode shows other characters.
+in section \\ref % phrase should have ~ between section and ref
+section~\\ref % capitalize capitalize section when saying Section 6.
+\\(sub)?section\{Intro\} % syntax spell it out.

data/lib/rules/misspellings

@@ -0,0 +1,33 @@
+asess                % spelling
+elimintate           % spelling
+enginner             % spelling
+experiements         % spelling
+measurment           % spelling
+pathlogies           % spelling
+secrurity            % spelling
+taht                 % spelling
+teh                  % spelling
+thrid                % spelling
+accrurate            % spelling
+prevalance           % spelling prevalence
+upto                 % spelling not a word, should be "up to"
+til                  % spelling not a word, should be "until"
+thes                 % spelling indecisive these/the
+accurarte            % spelling
+suppots              % spelling
+privledge            % spelling "privilege" I misspell it every way possible.
+privlege             % spelling "privilege" I misspell it every way possible.
+priviledge           % spelling "privilege" I misspell it every way possible.
+infomation           % spelling
+queueing             % spelling I'd love to spell it this way, but spellchecker whines.
+vatnage              % spelling argh.
+hte                  % spelling
+acknowledgement      % spelling acknowledgment, though what you have is technically legal, despite ispell.
+acknowlegement       % spelling needs a d.
+acknowlegment        % spelling needs a d.
+acknowledgements     % spelling acknowledgment , though what you have is technically legal, despite ispell.
+acknowlegements      % spelling needs a d.
+acknowlegments       % spelling needs a d.
+targetted            % spelling "targeted"
+desireable           % spelling "desirable"
+fullproof            % spelling found this in savage et al. traceback

data/lib/rules/my-rules

@@ -0,0 +1,60 @@
+#  such may be abused to blacklist certain words even spelled correctly.
+# capitalize is case sensitive, and also bracketed by non-word.
+# phrase and spelling are case insensitive, but bracketed by non-word characters.
+# syntax is case sensitive but not bracketed by non-word; probably best if used with regexes.
+\bet al\.[^}]        % syntax use the \etal{} command instead. (or write one to italicize)
+\bet\. al\.          % syntax use the \etal{} command, "et" needs no dot (et alii). (or write one to italicize)
+\bc\.f\.\b             % syntax should be cf. for "confer" (latin for compare)
+\b$i\)[^$]              % syntax leave the paren in math mode -- should be $i)$
+\b$ii\)[^$]             % syntax leave the paren in math mode -- should be $ii)$
+\b$iii\)[^$]            % syntax leave the paren in math mode -- should be $iii)$
+\b$iv\)[^$]             % syntax leave the paren in math mode -- should be $iv)$
+\b$v\)[^$]              % syntax leave the paren in math mode -- should be $v)$
+\ban [b-df-gj-np-tv-z] % syntax probably meant to use "a" instead of "an", though there are exceptions.
+\ban [B-DF-GJ-NP-TV-Z][^A-Z/] % syntax probably meant to use "a" instead of "an", though there are exceptions (like acronyms).
+\b[Aa] [aeiouAEIOU](?!se|ni|A|ur|RL|ti|ne|DP) % syntax probably meant to use "an" instead of "a", though there are exceptions. (user, useful, AA, unified, uniform, unique, Europe, one, UDP; n/a doesn't work, so use {n/a})
+This allows           % phrase tie more explicitly: This (x) allows...
+try and               % phrase "try to", though if you're using try as a noun in a compound sentence, this rule is wrong.
+impact of             % phrase not a useful metaphor; try evaluation, success, effect, value.
+including [^\.]*etc\. % syntax "including" tells of a non-exclusive list, so "etc." is redundant.  This rule will misfire if you have two lists in your sentence, but you shouldn't do that either. ;)
+includes [^\.]*etc\.  % syntax "includes" tells of a non-exclusive list, so "etc." is redundant.  This rule will misfire if you have two lists in your sentence, but you shouldn't do that either. ;)
+and etc\.             % phrase come on. learn some latin.
+AT&T                  % syntax you poor thing, this won't compile.
+doesn't               % phrase be formal.
+be occur              % phrase what happens when I'm indecisive about what follows "can"
+up until              % phrase "until"
+one or more           % phrase probably redundant -- nonzero is probably implied.
+is comprise(d|s) of   % phrase you probably mean "is composed of" because "comprises" is more a synonym for "contains" 
+will be significantly different % phrase "will differ significantly" for active voice
+More importantly,     % phrase probably means the order is wrong: put important stuff first.
+todo                  % ignoredcommand
+texttt                  % ignoredcommand
+due to space constraints % phrase don't whine.
+this paper % phrase can be ambiguous if talking about someone else's paper whether you mean the one youre writing or the one you're talking about..
+the above             % phrase horrible phrase that must be expunged.  you might use "these" instead, but best to make the sentence stand alone.
+referred to above     % phrase "these".
+(all|the|of) [0-9][ ] %  phrase use words for numbers in phrases.
+clearly shows         % phrase "clearly" is usually much.
+grows larger          % phrase is "grows smaller" possible?  grows.
+guarantee as much as possible % phrase then not really a guarantee "provide"
+affects negatively   % phrase "hurts" or "harms"
+rely upon % phrase rely on is good enough
+relies upon % phrase relies on is good enough
+record route packets? % phrase hyphenate record-route packets
+record-route; % phrase leave record route alone if not modifying something else
+we accomplish this  % phrase verbose way to get active voice.
+refers to the % phrase you're being wimpy in the definition.  use "is"
+\\emph\{[a-zA-Z ]*\} refers to % syntax you're being wimpy in the definition.
+loss off % phrase loss of?
+this could % phrase this "what" could
+with that has % phrase probably just one
+simply % phrase probably isn't.
+to get to % phrase "to reach"?
+latency benefit % phrase reduction
+latency improvement % phrase reduction
+shed insight % phrase 'shed light' would seem the metaphor.
+increasingly more % phrase redundant
+I\.e\. % syntax starting a sentence with i.e. is just ugly.
+E\.g\. % syntax starting a sentence with e.g. is just ugly.
+in the large % phrase if large is a noun, bad.  if it's an adjective, fine.
+encapsulates with % phrase seen it, don't know what it means.

data/lib/rules/networking-research

@@ -0,0 +1,50 @@
+EBONE                % capitalize a somewhat useless rule, now (we standardized on Ebone)
+EBone                % capitalize a somewhat useless rule, now (we standardized on Ebone)
+IPs                  % phrase should be IP addresses
+NMI                  % spelling is Steve's cat's name, not a measurement system
+Planetlab            % capitalize PlanetLab
+Send-Train           % capitalize should be Send-train 
+UUNET                % capitalize UUnet
+[Rr]ate-limits       % spelling "rate limits" has no hyphen, only "rate-limited"
+[a-z] Tier           % syntax don't capitalize Tier unless at the beginning of the sentence
+``no-valley''        % spelling should not be quoted, it's distracting
+best effort          % phrase hyphenate best-effort service.
+bpf                  % capitalize
+ccdf                 % capitalize
+cisco                % capitalize the company name
+city-pairs           % phrase decided to hyphenate
+deliver route        % phrase jargon redundancy
+euclidean % capitalize Euclidean.
+interdomain          % spelling inter-domain
+internet             % capitalize unless talking about an internet other than the Internet
+intradomain          % spelling intra-domain
+load\bbalanc         % syntax load-balanced links, hyphenate load-balancing too
+log-normal           % spelling lognormal is one word.
+magic-packet         % spelling don't hyphenate
+multiaccess          % spelling multi-access (or better, multiple access)
+namespace            % spelling two words
+nimi                 % capitalize
+no\bvalley           % phrase hyphenate no-valley
+pareto               % capitalize
+planetlab            % capitalize PlanetLab
+points links         % phrase probably wrong to have two plural nouns adjacent
+scriptroute          % capitalize
+send-train           % capitalize should be Send-train 
+tier [123]           % phrase should be tier-1, tier-2, or tier-3.
+tier-[123]s          % phrase should be tier-1 ISPs
+ttl                  % capitalize
+weibull              % capitalize proper name.
+PoP                  % syntax I think POP looks less annoying.
+PoPs                 % syntax I think POP looks less annoying.
+the general Internet % phrase it's just the Internet.  there is only one.
+IP-ID                % phrase spell it out
+handful of routers   % phrase they don't fit in your hand
+outdegree            % phrase going to use hyphenated form.
+network measurement algorithms % phrase you're too kind to network measurement.  I haven't seen an algorithm yet.
+http[ ]              % capitalize capitalize HTTP.
+linux                % capitalize capitalize Linux
+Internet[^\.]*Internet % syntax avoid Internet twice in the same sentence?
+zipf                 % capitalize capitalize the guy's name.
+in network distance % phrase what is that?
+TIMEWAIT % spelling it's "TIME-WAIT", hyphenated in rfc 793
+FINWAIT % syntax it's "FIN-WAIT-1" or "FIN-WAIT-2", hyphenated in rfc 793

data/lib/rules/passive-voice

@@ -0,0 +1,19 @@
+it is possible to                   % phrase passive voice, try: "can"
+are identified by                   % phrase passive
+is shown                            % phrase passive.
+is not included in                  % phrase maybe this is passive
+there (are|is) [^\.:;]* (that|in)   % phrase maybe this is passive
+can be evaluated                    % phrase avoid passive: I evaluated
+can be observed                     % phrase avoid passive: are visible
+# is needed                         % phrase passive voice
+is used to                          % phrase go active voice, or subsititute "helps"
+(are|were) needed[^\?]              % phrase passive voice
+(is|are) presented in               % phrase "appears in", or reword to avoid passive voice
+it is possible that                 % phrase "may"
+(is|are) (depicted|illustrated|sketched) in  % phrase thats passive voice
+(is|are) shown in                   % phrase "shows"
+as can be seen in                   % phrase X shows that Y.
+there needs to be                   % phrase passive voice in a bad way.
+was designed                        % phrase passive voce.
+it may be                           % phrase passive "it"
+it is important that                % phrase passive; replace with X is important because Y.

data/lib/rules/verbose-phrases

@@ -0,0 +1,229 @@
+a large number of                   % phrase you mean "many"
+a substantial number of             % phrase how substantial?  most?  or just enough that can't be ignored?
+an insufficient number of           % phrase "too few"
+a significant number of             % phrase one is significant.   consider "prohibitive" if the number is sufficient to be problematic.
+a number of                         % phrase getting the verb agreement for this useless phrase is tricky.
+a number of different               % phrase use "different" (should have a high score)
+a small number of                   % phrase you mean "few"
+a low number of                   % phrase you mean "few"
+a relatively low number of                   % phrase you mean "few"
+actually                            % spelling probably doesn't add
+and instead                         % phrase replace with but?
+be done                             % phrase if "X of Y can be done", try "Y can be Xed"; it's already passive voice.
+combining multiple                  % phrase as opposed to "combining one?"
+aggregating multiple                % phrase "aggregating"
+do this                             % phrase probably verbose if you use a pronoun for what you're doing
+exists[ ]                           % phrase probably no better than "is", but end of sentence may be unavoidable?
+if it is to                         % phrase should be "to" (usually followed by "be X")
+if they are to                      % phrase should be "to" (usually followed by "be X")
+in general                          % phrase unless matched with "in specific," this is usually useless; perhaps "overall"
+in order to                         % phrase remove "in order" and get "to"
+in the past                         % phrase past tense is likely enough.
+in the way of                       % phrase should be "as"
+counting the number of              % phrase counting.  dude.
+is permitted to                     % phrase "may"
+largely opaque                      % phrase largely does not modify opaque
+makes a new                         % phrase should be "creates"
+may not chose                       % phrase "may not" is future tense; "chose" is past.
+one should note                     % phrase just write it.
+note that                           % phrase is the rest of the paper less notable?
+Note, that                          % syntax not only should you not "note that", no comma after note.
+we note                             % phrase is the rest of the paper less notable?
+note however that                   % phrase is the rest of the paper less notable?
+it is important to note             % phrase is the rest of the paper less notable?
+really                              % phrase probably doesn't add; if you think it does, use "r{}eally" -- don't change to 'in fact'
+rigorously                          % spelling probably doesn't add, and I rarely do anything with rigor
+the way in which                    % phrase should be "how" or "" 
+the manner in which                 % phrase should be "how" or "" 
+value stems                         % phrase value is derived or offered, I think.
+time at which                       % phrase very likely "when"
+place at which                      % phrase very likely "where"
+at the time                         % phrase very likely "when"
+reduced number of                   % phrase very likely "fewer" or maybe maybe "less"
+is present in                       % phrase present is probably redudant, try "is in"
+they all                            % phrase maybe "all xs" would be better.
+easy to do                          % phrase "feasible" or "practical" might be better.
+is going to                         % phrase "will".
+are going to                        % phrase "will".
+getting                             % phrase probably "receiving" or "querying"
+those are                           % phrase see if "those X are" is clearer?
+design is motivated                 % phrase "inspired by" is probably better than "motivated" for design
+locations throughout the world      % phrase drop "throughout the world"
+e.g., as opposed to                 % phrase if you're giving examples, you're not talking about what isn't.  drop "e.g."
+in addition, we also                % phrase remove either "also" or "in addition"
+other related issues                % phrase probably remove "other"
+the aforementioned                  % phrase "these xs" or "this x" would be less snooty
+center around                       % phrase (cook) a center is a point: "center on" is okay.
+could care less                     % phrase (cook) 'really? how much less could you care?' (should be couldn't)
+grouped together                    % phrase redundant.  "grouped" alone should suffice.
+put together                        % phrase long: "construct" "build" or "assemble"
+consistent with each other          % phrase redundant.  "consistent" suffices.
+be accomplished with                % phrase try "requires" "uses" "needs"?
+the lack of knowledge of            % phrase would "X is unknown" work better?
+gets to know                        % phrase you mean "learns"
+trying to look like                 % phrase you mean "acting", "emulating", or "mimicing"
+has got to be                       % phrase "must be"
+got                                 % phrase try "became" "received" ?
+gotten                              % phrase try "helped" ?
+live in a vacuum                    % phrase a tired metaphor that makes me want to vomit.  
+positive impact                     % phrase try "benefit"
+negative impact                     % phrase try "harm" or "consequences"
+adverse impact                      % phrase try "harm" or "consequences"
+adversely impacting                 % phrase try "harming" or "hurting"
+discuss the issues of               % phrase could probably drop "the issues of" unless there's a list
+the presence of                     % phrase not far from 'is', 'has', etc.
+does not allow                      % phrase consider "forbids" or "prohibits"
+and/or                              % phrase just say or.
+there is the potential to           % phrase just say may.
+there is the possibility that       % phrase just say might.
+can be achieved                     % phrase maybe not so good?
+find out                            % phrase perhaps determine?
+in the absence of                   % phrase perhaps without?
+in the presence of                  % phrase perhaps with?
+set up                              % phrase perhaps create, configure, or initialize
+in the face of                      % phrase can be overused.  try despite?
+several times (at|of)               % phrase discouraged by Kurt.
+a large degree of                   % phrase ick.
+we start by first                   % phrase redundant. ("first, we" or "we start by").
+in general, they are usually        % phrase redundant.
+refers to the notion                % phrase define your term precisely if possible.
+a significant amount of             % phrase probably just "significant"
+real practical                      % phrase as opposed to imaginary practical?
+people that are                     % phrase use people who are?
+additional detail that we add       % phrase as opposed to additional detail that we subtract?
+in some cases and not in others     % phrase "in some cases"
+it is known that                    % phrase just say it.
+caused due to                       % phrase "caused by"
+a result of the fact that           % phrase "caused by"
+can be attributed to the fact that  % phrase "is because"
+a large set of                      % phrase probably don't care that it is a set.
+a small set of                      % phrase probably don't care that it is a set: use 'a few' 
+provides a look at                  % phrase (timid) probably mean "shows".
+in most cases                       % phrase "usually"
+continue into the forseeable future % phrase "continue".
+for the forseeable future           % phrase drop.
+fail to successfully                % phrase "fail to" is sufficient.
+Clearly,                            % syntax starting a sentence with clearly confuses me.
+in different continents             % phrase ON different continents, IN different countries
+(we|to) handle                      % phrase use a more specific verb like address, treat, solve
+handling                            % phrase use a more specific verb like addressing, treating, solving, mitigating (unless handling errors or exceptions)
+For the purposes of                 % phrase "For"
+We observe that                     % phrase drop.
+some degree of                      % phrase "some"
+in the problem of                   % phrase (contributed by rap)
+conclude several things             % phrase make (draw) several conclusions
+extra bonus                         % phrase "bonus"
+added bonus                         % phrase "bonus"
+it is important to emphasize that   % phrase use diction to emphasize.
+it is possible that                 % phrase "x may y"
+caused due to                       % phrase "caused by"
+recent work by                      % phrase could maybe be dropped, as the cite will include the date.
+identify the location of            % phrase "find"
+that go across                      % phrase "that cross"
+ideally, we would like              % phrase "we would like"
+enabling the ability to             % phrase "supporting" or "allowing" or "permitting"
+absolutely essential                % phrase essential is.
+we essentially do                   % phrase essentially is a poor adverb.  "The essence of our algorithm is a..."
+Essentially,                        % phrase maybe "In essence," but could also be removed.
+In this section (we|I)              % phrase "In this section, we", or "In this section, I"
+essentially all                     % phrase "most"
+past experience                     % phrase "experience" http://www.cmu.edu/styleguide/trickywords.html
+particulary difficult primarily     % phrase simplify
+intuition about why                 % phrase "intuition as to why"
+Recall from above                   % phrase "recall"
+Further, (I|we) will also           % phrase drop further or also
+respectively                        % phrase unneeded.
+in terms of                         % phrase don't need this.
+the extent to which                 % phrase "how much"
+make sure                           % phrase "ensure"
+make up                             % phrase "constitute" "compose"
+make a decision                     % phrase "decide"
+make a guess                        % phrase "guess"
+since that time                     % phrase "since then"
+choices to make                     % phrase "choices"
+certain limitations                 % phrase what does 'certain' add to limitations?
+will [a-z]* in the future           % phrase "will"
+business entities                   % phrase "businesses"
+rely primarily on                   % phrase "primarily" weakens "rely".  perhaps just "use" would be simpler.
+has the potential to                % phrase can
+have not yet developed              % phrase "have yet to develop"
+to be effective,                    % phrase probably redundant.
+provide information about           % phrase "tell how" "reveal" "expose" "disclose"
+are different,                      % phrase "differ"
+have already been                   % phrase "have been"? "were"?
+as appropriate                      % phrase not needed?
+only rarely                         % phrase "rarely" is probably enough.
+is effective at                     % phrase "can"
+foremost among them is              % phrase "foremost is" would be shorter.
+those that have no                  % phrase those without
+that have no                        % phrase "without"?
+a variety of diverse                % phrase redundant
+be highly valuable in               % phrase simplify.
+the overall goal                    % phrase 'the goal'
+sometimes an? [a-z]+ will           % phrase an x may
+this is perhaps because             % phrase this may be because
+adding an additional                % phrase redundant
+IP protocol                         % phrase redundant
+works well                          % phrase be more specific.
+something                           % phrase could eliminate.
+to keep from                        % phrase "to avoid"
+[\.,] since (!then)                 % phrase probably you mean "because" unless you're talking about time. -- "has since" is okay.
+performance characteristics         % phrase rare that characteristics adds.
+takes into account                  % phrase considers
+specify particular                  % phrase if specifying, particular should be redundant.
+prototype implementation            % phrase "implementation" is redundant.
+given a particular                  % phrase "given a" is probably enough
+described in detail (in|below)      % phrase use "detailed"
+relatively more                     % phrase more is already relative.
+focus primarily on                  % phrase bad metaphor: subject of focus is singular.
+primary focus                       % phrase bad metaphor: subject of focus is singular.
+relatively more                     % phrase more is already relative.
+gives [a-z]+ [a-z]+ information about % phrase use "tells" x
+gives [a-z]+ information about      % phrase use "tells" x
+an important question to ask is     % phrase just ask it.
+an interesting thing                % phrase avoid saying something is interesting.  if you have to say it, it isn't.
+checks to see if                    % phrase "checks" or "determines"
+have an effect on                   % phrase "affect"
+an important question to ask is     % phrase just ask it.
+an interesting thing                % phrase avoid saying something is interesting.  if you have to say it, it isn't.
+checks to see if                    % phrase "checks" or "determines"
+we can see                          % phrase "we can see" isn't formal enough.
+still remain                        % phrase "remain".
+change over time                    % phrase "change"
+turn into                           % phrase "become"
+looking back in retrospect          % phrase pick.
+ensures that there will be no       % phrase "prevents"
+does have                           % phrase "has"
+first step toward this              % phrase "toward this" can probably be dropped.
+can potentially be                  % phrase "might be", or just "can be"
+obviates the need for               % phrase just obviates x, not obviates the need for x.
+it is indeed                        % phrase "it is", though still passive.
+planning in advance                 % phrase when else might you plan?
+a lot of                            % phrase "many"
+keep in mind                        % phrase "consider" (or drop)
+it is clear that                    % phrase if clear, you don't have to say it.
+especially true                     % phrase true is an absolute, can't be especially true.
+making it increasingly difficult    % phrase preventing, discouraging, impeding, blocking, slowing...
+is potentially                      % phrase "may be"
+have been [a-z]* in the past        % phrase 'in the past' is redundant with tense.
+amount of time  % phrase "duration"
+should ideally % phrase "should"
+are of great benefit to % phrase "help" or "aid"
+are of benefit to % phrase "help" or "aid" or "promote"
+important here % phrase consider "relevant"
+while at the same time % phrase "while" is enough.
+are able to % phrase can
+subvert the proper operation of % phrase subvert
+speed slow % phrase speed is probably redundant.
+of size no smaller than % phrase "of size" is probably redundant
+of size no larger than % phrase "of size" is probably redundant
+of size smaller than % phrase "of size" is probably redundant
+of size larger than % phrase "of size" is probably redundant
+might potentially % phrase "might"
+in the context of % phrase "in" avoid, if possible.
+increase the amount of % phrase probably just increase.
+show the difference between % phrase compare
+in addition, we also % phrase pick.
+overhead efficiency % phrase huh?
+have an effect on % phrase "affect"
+have a signficant effect on %  phrase "affect"

data/lib/style-check.rb

@@ -0,0 +1,254 @@
+#!/usr/bin/env ruby
+
+# enough that the main code can find these rules.
+Gem_Ruleset_Path = File.dirname(__FILE__) + "/rules"
+test(?e, Gem_Ruleset_Path) or raise "gem installed incorrectly; rules directory not found"
+
+Gem_Rulesets = Dir.glob(Gem_Ruleset_Path + "/*") 
+
+#!/usr/bin/env ruby
+
+# copyright 2004 Neil Spring
+# distributed under the terms of the GNU General Public License.
+
+# a simple script to check against a ruleset of "forbidden"
+# phrases and spellings.  it is intended as a quick check
+# against verbose phrases, overused expressions, incorrect
+# spellings, and inconsistent capitalization or hypenation.
+
+# complexity in this script arised from handling basic tex
+# comments and ignoring fragments of tex that are allowed to 
+# violate style (such as the bibtex tag inside \cite{})
+
+# the dictionary of censored phrases is a compound of
+# ~/.style-censor, ./censor-dict (for historical reasons),
+# and /etc/style-censor, as well as all files in
+# ~/.style-check.d, for particularly egregious violations
+# (such as spelling errors and common double-word problems).
+
+# this script is not intended to substitute for a spell
+# checker, a grammar checker, or a proof-reader.  And the 
+# phrases listed aren't necessarily forbidden; they may 
+# simply be discouraged.  Those that are particularly weak
+# should be annotated with a question mark at the end of the
+# explanation.  (the behavior of the script does not currently
+# depend on this syntax.  someday it may.)
+
+# Bugs 
+
+# - misspelled words may not be recognized if capitalized.
+# This is a consequence of the script's goal of watching for
+# uniform upper- and lower- case project names and such.  
+
+# - expressions with % in them won't be matched; the %
+# character is reserved for explanatory text.
+
+# if run with -g, insert a space between line and column,
+# so that gedit linkparser.py at least parses the file and 
+# line number
+Gedit_Mode = if(ARGV.include?("-g"))
+               ARGV.delete("-g")
+               true
+             else
+               false
+             end
+
+if(ARGV[0] == "-v") then
+  ARGV.shift
+  $VERBOSE = true
+end
+
+override_rule_paths = nil
+if(ARGV[0] == "-r") then
+  ARGV.shift
+  param = File.expand_path(ARGV.shift)
+  if(test(?d, param)) then
+    override_rule_paths = Dir.glob(param + "/*")
+  elsif(test(?f, param)) then
+    override_rule_paths = param
+  else
+    raise "what is that rule path you tried to specify?"
+  end
+end
+
+$exit_status = 0
+
+ignoredCommands = "ref|href|url|input|bibliography|cite|nocite|cline|newcommand|includegraphics|begin|end|label".split('|')
+PctCensored_phrases = Hash.new  # before stripping comments
+PreCensored_phrases = Hash.new  # before stripping cites
+Censored_phrases = Hash.new     # the rest.
+PathList = if(override_rule_paths) then 
+             override_rule_paths
+           else
+             (Gem_Rulesets ? Gem_Rulesets : [] ) + 
+               Dir.glob("/etc/style-check.d/*") + 
+               Dir.glob(ENV["HOME"] + "/.style-check.d/*") + 
+               [ ENV["HOME"] + "/.style-censor", "./censor-dict", "/etc/style-censor", "./style-censor" ]
+           end
+
+# $prefilter = nil
+
+PathList.map { |rulefilename| 
+  if ( Kernel.test(?f, rulefilename) && rulefilename !~ /~$/ ) then
+    # $stderr.print "loading #{rulefilename}"
+    File.open(rulefilename).each_with_index { |phr,lnnum_minus_one|
+      #if ( ! phr.scan(~ /^# / ) then 
+      expression, reason = phr.split(/\s*%\s*/) 
+      if( reason ) then 
+        begin
+          Censored_phrases[ 
+            case reason.split(/\s+/)[0]
+            when 'syntax'
+              Regexp.new(expression.chomp) 
+            when 'capitalize'
+              Regexp.new('\b' + expression.chomp + '\b' ) 
+            when 'phrase' 
+              # $stderr.puts('\b' + expression.chomp.gsub(/ +/, '\s+').gsub(/([a-zA-Z])$/, '\1\b')) 
+              Regexp.new('\b' + expression.chomp.gsub(/ +/, '\s+').gsub(/([a-zA-Z\)])$/, '\1\b'), Regexp::IGNORECASE ) 
+            when 'spelling' 
+              Regexp.new('\b' + expression.chomp + '\b', Regexp::IGNORECASE ) 
+            when 'ignoredcommand'
+              ignoredCommands.push(expression.chomp)
+              nil
+            else
+              puts "warning: no class specified for %s at %s:%d" % [ expression, rulefilename, lnnum_minus_one + 1 ]
+              Regexp.new('\b' + expression.chomp + '\b' ) 
+            end
+          ] = ( reason or "" ) + "  (matched '" + expression.chomp + 
+            "' in %s:%d)" % [ rulefilename, lnnum_minus_one + 1 ]
+          # end
+        rescue RegexpError => e
+          $stderr.puts "#{rulefilename}:#{lnnum_minus_one + 1}: Error: #{e}"
+          exit 1
+        end
+        Censored_phrases.delete(nil)
+      end
+    }
+    else 
+    []
+  end
+}
+
+Censored_phrases.delete_if { |regex,reason|
+  t = reason.split(/\s+/)[1] =~ /ignore/
+  if t then
+    puts "deleting #{regex} / #{reason}"
+  end
+  t
+}
+
+# $prefilter = Regexp.new( "(" + Censored_phrases.keys.map { |r| r.source}.join("|") + ")" )
+
+# thanks to Adin Rivera for reporting a little bug in the next line.
+PreCensored_phrases[ 
+  Regexp.new(/\.~?\\cite/) ] = "~\\cite{} should precede the period."
+PreCensored_phrases[ 
+  Regexp.new(/\b(from|in|and|with|see)[~ ]+\\cite/) ] = "Don't cite in the sentence as 'in [x]', cites are not nouns.  Prefer: Smith et al.~\\cite{...} show ... ."
+PreCensored_phrases[ 
+  Regexp.new(/[^\.\n]\n\n/) ] = "paragraphs should end with a sentence end"
+PreCensored_phrases[ 
+  Regexp.new(/(Table|Figure|Section)[ \n]\\ref/) ] = "Table, Figure, and Section refs should have a non-breaking space"
+PreCensored_phrases[ 
+  Regexp.new(/(table|figure|section)~\\ref/) ] = "Table, Figure, and Section refs should be capitalized"
+PreCensored_phrases[ 
+  Regexp.new(/\\url\{(?!http|ftp|rtsp|mailto)/) ] = "~\\url{} should start with http:// (or ftp or rtsp or maybe mailto)."
+
+PctCensored_phrases[ 
+  Regexp.new(/[0-9]%/) ] = "a percent following a number is rarely an intended comment."
+# PctCensored_phrases[ 
+#   Regexp.new(/[<>]/) ] = "a less than or greater than outside math mode shows other characters."
+
+if(Censored_phrases.length == 0) then
+  puts "no style-censor phrases found.  write some in ./style-censor."
+  exit 1
+end
+De_comment = Regexp.new('(([^\\\\]%.*)|(^%.*))$')
+# though newcommand could gobble both parameters...
+De_command = Regexp.new('(~?\\\\(' + ignoredCommands.join('|') + ')(\[[^\]]*\])?\{[^{}]*\})')
+De_verb = Regexp.new('\\\\verb(.)[^\1]*\1')
+De_math = Regexp.new('[^\\\\]\$.*[^\\\\]\$|^\$.*[^\\\\]\$')
+
+def do_cns(line, file, linenum, phra_hash)
+  # if line =~ /\\caption/ && file =~ /Mapping/ then
+    # puts "validating: '#{line}'"
+  # end
+  m = nil
+  r = nil # so we can keep it as a side-effect of the detect call
+  detected = nil
+  windows_detect_bug_avoider = nil
+  # if m = $prefilter.match(line) then
+    if(detected = phra_hash.keys.detect { |r| m = r.match(line) and (line.index("\n") == nil or m.begin(0) < line.index("\n"))  } ) then
+      matchedlines = ( m.end(0) <= ( line.index("\n") or 0 ) ) ? line.gsub(/\n.*/,'') : line.chomp
+      puts "%s:%d:%s%d: %s (%s)" % [ file, linenum, Gedit_Mode ? ' ': '', m.begin(0)+1, matchedlines, m.to_s.tr("\n", ' ') ]
+      $exit_status = 1 if(!phra_hash[detected] =~ /\?\s*$/) 
+      if($VERBOSE && phra_hash[detected]) then
+        puts "  " + phra_hash[detected]
+        phra_hash[detected] = nil # don't print the reason more than once
+      end
+    end
+  # end
+end
+ 
+Input_files = ARGV
+Input_files.delete_if { |f|
+  if !test(?e, f) then
+    $stderr.puts "WARNING: Input file #{f} does not exist.  skipping."
+    true
+  else
+    false
+  end  
+}
+Input_files.each { |f|
+  in_multiline_comment = 0
+  in_multiline_verbatim = false
+  in_multiline_equation = false
+  # load the file, contents, but drop comments and other
+  # hidden tex command pieces
+  lines = File.open(f).readlines
+  lines.each_with_index { |ln,i|
+    do_cns( ln, f, i+1, PctCensored_phrases )
+    ln.sub!(De_comment, '')
+    # no, I don't know that comment environments nest and verbatim environments dont. 
+    # I have no such cluefulness.
+    if( ln =~ /\\begin\{comment\}/ ) then
+      in_multiline_comment+=1
+    elsif( ln =~ /\\end\{comment\}/ ) then
+      in_multiline_comment-=1
+    end
+    if( ln =~ /\\begin\{verbatim\}/ ) then
+      in_multiline_verbatim=true
+    elsif( ln =~ /\\end\{verbatim\}/ ) then
+      in_multiline_verbatim=false
+    end
+    if( ln =~ /\\begin\{(equation|math|eqnarray)\*?\}/ ) then
+      in_multiline_equation=true
+    elsif( ln =~ /\\end\{(equation|math|eqnarray)\*?\}/ ) then
+      in_multiline_equation=false
+    end
+    if(in_multiline_comment == 0 && ! in_multiline_verbatim && ! in_multiline_equation)  then
+      do_cns( ln, f, i+1, PreCensored_phrases )
+      ln.gsub!(De_command, '~')
+      ln.gsub!(De_verb, '~')
+      ln.gsub!(De_math, '~')
+      do_cns( (ln + ( lines[i+1] or "" ) + ( lines[i+2] or "" )).sub(De_comment, '').sub(De_command, '~'), f, i+1, Censored_phrases )
+      
+      # now try to make sure that paragraphs end with sentence
+      # ending punctuation, such as a period, exclamation mark,
+      # question mark, or perhaps a command-ending brace.
+      if(lines.length > i+3) then
+        checkstring = lines[i..(i+1)].map { |ln| 
+          ln.sub!(De_comment, '');   
+          ln.sub!(/\\[a-z]+=[0-9]+/, '');  # tex variable assignment; I format each on its own line.
+          ln }.join 
+        #if(checkstring =~ /SIGCOMM/) then
+          #puts "%s:%d: argh: %s" % [ f, i, checkstring.gsub(/\n/, '\n') ];
+        #end
+        if(checkstring =~ /[a-z0-9][^\.\:\!\?\n}]\n\n/) then
+          puts "%s:%d: apparent bad paragraph break: %s" % [ 
+            f, i+1, checkstring.gsub(/\n/, '\n') ];
+        end
+      end
+    end
+  }
+}
+    

metadata

@@ -0,0 +1,61 @@
+--- !ruby/object:Gem::Specification
+name: style-check
+version: !ruby/object:Gem::Version
+  version: '0.15'
+platform: ruby
+authors:
+- Neil Spring
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-12-06 00:00:00.000000000 Z
+dependencies: []
+description: |-
+  style-check.rb searches latex-formatted text in search of forbidden phrases and
+      prints error messages formatted as if from a compiler.
+email: nspring@cs.umd.edu
+executables:
+- style-check.rb
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/style-check.rb
+- lib/style-check.rb
+- lib/rules/bad-words
+- lib/rules/barrass
+- lib/rules/cliche
+- lib/rules/common-typos
+- lib/rules/day-gastel
+- lib/rules/foolish-phrases
+- lib/rules/latex-checking
+- lib/rules/misspellings
+- lib/rules/my-rules
+- lib/rules/networking-research
+- lib/rules/passive-voice
+- lib/rules/verbose-phrases
+homepage: http://www.scriptroute.org/
+licenses:
+- GPL
+metadata: {}
+post_install_message: "Now run: \n% style-check.rb *.tex"
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.14
+signing_key: 
+specification_version: 4
+summary: Style checker for LaTeX
+test_files: []
+has_rdoc: