Skip to content

Commit

Permalink
Making docstrings javadoc
Browse files Browse the repository at this point in the history
  • Loading branch information
@datamacgyver
datamacgyver committed Aug 26, 2018
1 parent 57ebd34 commit 61888f8
Show file tree
Hide file tree
Showing 2 changed files with 410 additions and 422 deletions.
147 changes: 70 additions & 77 deletions StringTools.ecl
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,21 +3,20 @@
EXPORT StringTools := MODULE

EXPORT regexLoopRec := {STRING Regex; STRING repl};
EXPORT regexLoop(STRING inStr, DATASET(regexLoopRec) regexDS, BOOLEAN noCaseRegex = TRUE, BOOLEAN TidyToo = TRUE) := FUNCTION

/* -------------------------------------------------------------
Loops through two sets and conducts a number of regex substitutions.
Takes a database containing regex and replacement (see above RECORD, RegexLoopRec).
Note this NOCASES by default.
@param inStr String - text to be replaced
@param regexDS DataSet - See above recordset (RegexLoopRec). List of from and to strings, from can be a regex and replacement can contain capture groups.
@param noCaseRegex Boolean - Should the regex be conducted with nocase? Defaults to TRUE
@param TidyToo Boolean - Shoulde the strings be lowercased and trimmed left and right before commencing? Defaults to TRUE
@return - String with all regexs applied in order
-------------------------------------------------------------*/
EXPORT regexLoop(STRING inStr, DATASET(regexLoopRec) regexDS, BOOLEAN noCaseRegex = TRUE, BOOLEAN TidyToo = TRUE) := FUNCTION
/**
* Loops through two sets and conducts a number of regex substitutions.
* Takes a database containing regex and replacement (see above RECORD, RegexLoopRec).
*
* Note this NOCASES by default.
*
* @param inStr text to be replaced
* @param regexDS See above recordset (RegexLoopRec). List of from and to strings, from can be a regex and replacement can contain capturegroups.
* @param noCaseRegex Should the regex be conducted with nocase? Defaults to TRUE
* @param TidyToo Should the strings be lowercased and trimmed left and right before commencing? Defaults to TRUE
*
* @return String with all regexs applied in order
*/
LOCAL aString := IF(TidyToo, TRIM(std.Str.ToLowerCase(inStr), LEFT, RIGHT), inStr);
LOCAL regexDSBlankRow := DATASET([{' ',' '}], regexLoopRec);
LOCAL regexDSconcat := regexDSBlankRow + regexDS;
Expand All @@ -36,15 +35,14 @@ EXPORT StringTools := MODULE


EXPORT LongestWord (STRING InWords, STRING seperator = ' ') := FUNCTION

/* -------------------------------------------------------------
Takes a multi word string and returns just the longest word
@param InWords String - collection of words
@param seperator String - word seperator, defaults to space
@return - String of the longest word
-------------------------------------------------------------*/
/**
* Takes a multi word string and returns just the longest word
*
* @param InWords collection of words
* @param seperator word separator, defaults to space
*
* @return String of the longest word
*/

SplitWords := STD.Str.SplitWords(InWords, seperator);
WordDS := DATASET(SplitWords, {STRING words}); //Convert to DS
Expand All @@ -66,14 +64,14 @@ EXPORT StringTools := MODULE


EXPORT NumberSpacing (STRING InWords) := FUNCTION
/* -------------------------------------------------------------
Helps to create regex matchihng strings by allowing optional spaces between numbers.
Also controlls for presence of hyphens.
@param InWords String - Text to be modified
@return - text with optional regex spaces between numbers
-------------------------------------------------------------*/
/**
* Helps to create regex matching strings by allowing optional spaces between numbers.
* Also controls for presence of hyphens.
*
* @param InWords Text to be modified
*
* @return text with optional regex spaces between numbers
*/

ExtNumbers := REGEXREPLACE('([0-9])' , InWords , '[ ]?$1[ ]?');
noHyph := REGEXREPLACE('[ ]?-[ ]?' , ExtNumbers , '[ ]?');
Expand All @@ -85,16 +83,15 @@ EXPORT StringTools := MODULE


EXPORT ShortestWordDistance (STRING inString1, STRING inString2) := FUNCTION

/* -------------------------------------------------------------
Does a pairwise comparison of all words in each string,
returns the shortest distance between any two words.
@param inString1 String - Text to be compared 1
@param inString2 String - Text to be compared 2
@return - text of closest word present in both. Or '' if none
-------------------------------------------------------------*/
/**
* Does a pairwise comparison of all words in each string,
* returns the shortest distance between any two words.
*
* @param inString1 Text to be compared 1
* @param inString2 Text to be compared 2
*
* @return text of closest word present in both. Or '' if none
*/
//Extract must have's first as cannot be matching on two word strings and cannot be considering numbers as equal to letters.
split1 := DATASET(STD.Str.SplitWords(inString1, ' '), {STRING words;});
split2 := DATASET(STD.Str.SplitWords(inString2, ' '), {STRING words;});
Expand All @@ -119,33 +116,32 @@ EXPORT StringTools := MODULE


EXPORT allWordsPresentRegex (STRING aStr, STRING sep = ' ') := FUNCTION
/* -------------------------------------------------------------
Create a regex that takes each word in the input string and
states 'all these must be present to match'
@param aStr String - Text to be converted
@param sep String - word seperator, defaults to ' '
@return - Regex that will find all words in a string in any order
-------------------------------------------------------------*/
/**
* Create a regex that takes each word in the input string and
* states 'all these must be present to match'
*
* @param aStr Text to be converted
* @param sep word seperator, defaults to ' '
*
* @return Regex that will find all words in a string in any order
*/
aStr1 := REGEXREPLACE(sep, aStr, '\\\\b)(?=.*\\\\b');
aStr2 := '^(?=.*\\b' + aStr1 + '\\b).*$';
RETURN aStr2;
END;


EXPORT makeBOW(STRING aStr, STRING sep = ' ') := FUNCTION

/* -------------------------------------------------------------
Generates a unique, alphabetised word list from a string.
@param aStr String - Text to be converted
@param sep String - word seperator, defaults to ' '
@return - an alphabetised list of all words present.
TODO: SHOULD BE A MACRO, THIS IS CONVOLUTED.
-------------------------------------------------------------*/
/**
* Generates a unique, alphabetised word list from a string.
*
* @param aStr Text to be converted
* @param sep word seperator, defaults to ' '
*
* @return an alphabetised list of all words present.
*
* TODO: SHOULD BE A MACRO, THIS IS CONVOLUTED.
*/

lower := std.str.tolowercase(aStr);
noPunct := REGEXREPLACE('[^0-9a-z]', lower, ' ');
Expand All @@ -162,21 +158,18 @@ EXPORT StringTools := MODULE


EXPORT regexLoopOld(inStr, regex, replacement) := FUNCTIONMACRO

/* -------------------------------------------------------------
***DEPRICATION WARNING*** Use new version (at top of this module!)
Loops through two sets and conducts a number of regex substitutions.
Takes two Sets as regex and replacement.
@param inStr - a string to correct
@param regex - a set containing regex statements to sub
@param replacement - what to sub the regex statements with
@return - string with all regexes applied in order
-------------------------------------------------------------*/
/**
* DEPRICATION WARNING Use new version (at top of this module!)
*
* Loops through two sets and conducts a number of regex substitutions.
* Takes two Sets as regex and replacement.
*
* @param inStr a string to correct
* @param regex a set containing regex statements to sub
* @param replacement what to sub the regex statements with
*
* @return string with all regexs applied in order
*/

IMPORT std;

Expand Down
Loading

0 comments on commit 61888f8

Please sign in to comment.