Index: doc/theses/mike_brooks_MMath/string.tex =================================================================== --- doc/theses/mike_brooks_MMath/string.tex (revision 56ec508d488938933b41b33414874400c539d949) +++ doc/theses/mike_brooks_MMath/string.tex (revision 931f1b4f21d668a48981dfbe6830e8f2e8f9a384) @@ -7,4 +7,6 @@ \section{String Operations} + +% https://en.wikipedia.org/wiki/Comparison_of_programming_languages_(string_functions) \VRef[Figure]{f:StrApiCompare} shows a general comparison of string APIs for C, \CC, Java and \CFA. @@ -23,6 +25,6 @@ @strlen@ & @length@, @size@ & @length@ & @size@ \\ @[ ]@ & @[ ]@ & @charAt@ & @[ ]@ \\ -@strncpy@ & @substr@ & @substring@ & @( )@ \\ -@strncpy@ & @replace@ & @replace@ & @=@ \emph{(on a substring)}\\ +@strncpy@ & @substr@ & @substring@ & @( )@ RHS @=@ \\ +@strncpy@ & @replace@ & @replace@ & @( )@ LHS @=@ \\ @strstr@ & @find@ & @indexOf@ & @find@ \\ @strcspn@ & @find_first_of@ & @matches@ & @include@ \\ @@ -62,6 +64,6 @@ \begin{cquote} \sf -\begin{tabular}{@{}rrrrrl@{}} -\small\tt a & \small\tt b & \small\tt c & \small\tt d & \small\tt e \\ +\begin{tabular}{@{}rrrrll@{}} +\small\tt "a & \small\tt b & \small\tt c & \small\tt d & \small\tt e" \\ 0 & 1 & 2 & 3 & 4 & left to right index \\ -5 & -4 & -3 & -2 & -1 & right to left index @@ -72,12 +74,9 @@ \begin{cfa} #include @@ -@string@ s = "abcde", name = "MIKE", digit, alpha, punctuation, ifstmt; +@string@ s = "abcde", name = "MIKE", digit = "0123456789"; const char cs[] = "abc"; int i; -digit = "0123456789"; -punctuation = "().,"; -ifstmt = "IF (A > B) {"; -\end{cfa} -Note, the include file @string.hfa@ to access type @string@. +\end{cfa} +Note, the include file @@ to access type @string@. @@ -394,138 +393,155 @@ Extending the pattern to a regular expression is a possible extension. - -\subsection{Searching} - -The @index@ operation -\begin{cfa} -int index( const string & key, int start = 1, occurrence occ = first ); -\end{cfa} -returns the position of the first or last occurrence of the @key@ (depending on the occurrence indicator @occ@ that is either @first@ or @last@) in the current string starting the search at position @start@. -If the @key@ does not appear in the current string, the length of the current string plus one is returned. -%If the @key@ has zero length, the value 1 is returned regardless of what the current string contains. -A negative starting position is a specification from the right end of the string. +The replace operation returns a string in which all occurrences of a substring are replaced by another string. \begin{cquote} \setlength{\tabcolsep}{15pt} \begin{tabular}{@{}l|l@{}} \begin{cfa} -i = find( digit, "567" ); -i = find( digit, "567", 7 ); -i = digit.index( "567", -1, last ); -i = name.index( "E", 5, last ); -\end{cfa} -& -\begin{cfa} +s = replace( "PETER", "E", "XX" ); +s = replace( "PETER", "ET", "XX" ); +s = replace( "PETER", "W", "XX" ); +\end{cfa} +& +\begin{cfa} +"PXXTXXR" +"PXXER" +"PETER" +\end{cfa} +\end{tabular} +\end{cquote} +The replacement is done left-to-right and substituted text is not examined for replacement. + + +\subsection{Searching} + +The find operation returns the position of the first occurrence of a key string in a string. +If the key does not appear in the current string, the length of the current string plus one is returned. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +i = find( digit, '3' ); +i = "45" ^ digit; // python style "45" in digit +string x = "567"; +i = find( digit, x ); +\end{cfa} +& +\begin{cfa} +3 +4 + 5 -10 - - -\end{cfa} -\end{tabular} -\end{cquote} -The next two string operations test a string to see if it is or is not composed completely of a particular class of characters. -For example, are the characters of a string all alphabetic or all numeric? -Use of these operations involves a two step operation. -First, it is necessary to create an instance of type @strmask@ and initialize it to a string containing the characters of the particular character class, as in: -\begin{cfa} -strmask digitmask = digit; -strmask alphamask = string( "abcdefghijklmnopqrstuvwxyz" ); -\end{cfa} -Second, the character mask is used in the functions @include@ and @exclude@ to check a string for compliance of its characters with the characters indicated by the mask. - -The @include@ operation -\begin{cfa} -int include( const strmask &, int = 1, occurrence occ = first ); -\end{cfa} -returns the position of the first or last character (depending on the occurrence indicator, which is either @first@ or @last@) in the current string that does not appear in the @mask@ starting the search at position @start@; -hence it skips over characters in the current string that are included (in) the @mask@. -The characters in the current string do not have to be in the same order as the @mask@. -If all the characters in the current string appear in the @mask@, the length of the current string plus one is returned, regardless of which occurrence is being searched for. -A negative starting position is a specification from the right end of the string. -\begin{cfa} -i = name.include( digitmask ); $\C{// i is assigned 1}$ -i = name.include( alphamask ); $\C{// i is assigned 6}$ -\end{cfa} - -The @exclude@ operation -\begin{cfa} -int exclude( string &mask, int start = 1, occurrence occ = first ) -\end{cfa} -returns the position of the first or last character (depending on the occurrence indicator, which is either @first@ or @last@) in the current string that does appear in the @mask@ string starting the search at position @start@; -hence it skips over characters in the current string that are excluded from (not in) in the @mask@ string. -The characters in the current string do not have to be in the same order as the @mask@ string. -If all the characters in the current string do NOT appear in the @mask@ string, the length of the current string plus one is returned, regardless of which occurrence is being searched for. -A negative starting position is a specification from the right end of the string. -\begin{cfa} -i = name.exclude( digitmask ); $\C{// i is assigned 6}$ -i = ifstmt.exclude( strmask( punctuation ) ); $\C{// i is assigned 4}$ -\end{cfa} - -The @includeStr@ operation: -\begin{cfa} -string includeStr( strmask &mask, int start = 1, occurrence occ = first ) -\end{cfa} -returns the longest substring of leading or trailing characters (depending on the occurrence indicator, which is either @first@ or @last@) of the current string that ARE included in the @mask@ string starting the search at position @start@. -A negative starting position is a specification from the right end of the string. -\begin{cfa} -s = name.includeStr( alphamask ); $\C{// s is assigned "MIKE"}$ -s = ifstmt.includeStr( alphamask ); $\C{// s is assigned "IF"}$ -s = name.includeStr( digitmask ); $\C{// s is assigned ""}$ -\end{cfa} - -The @excludeStr@ operation: -\begin{cfa} -string excludeStr( strmask &mask, int start = 1, occurrence = first ) -\end{cfa} -returns the longest substring of leading or trailing characters (depending on the occurrence indicator, which is either @first@ or @last@) of the current string that are excluded (NOT) in the @mask@ string starting the search at position @start@. -A negative starting position is a specification from the right end of the string. -\begin{cfa} -s = name.excludeStr( digitmask); $\C{// s is assigned "MIKE"}$ -s = ifstmt.excludeStr( strmask( punctuation ) ); $\C{// s is assigned "IF "}$ -s = name.excludeStr( alphamask); $\C{// s is assigned ""}$ -\end{cfa} - - -\subsection{Miscellaneous} - -The @trim@ operation -\begin{cfa} -string trim( string &mask, occurrence occ = first ) -\end{cfa} -returns a string in that is the longest substring of leading or trailing characters (depending on the occurrence indicator, which is either @first@ or @last@) which ARE included in the @mask@ are removed. -\begin{cfa} -// remove leading blanks -s = string( " ABC" ).trim( " " ); $\C{// s is assigned "ABC",}$ -// remove trailing blanks -s = string( "ABC " ).trim( " ", last ); $\C{// s is assigned "ABC",}$ -\end{cfa} - -The @translate@ operation -\begin{cfa} -string translate( string &from, string &to ) -\end{cfa} -returns a string that is the same length as the original string in which all occurrences of the characters that appear in the @from@ string have been translated into their corresponding character in the @to@ string. -Translation is done on a character by character basis between the @from@ and @to@ strings; hence these two strings must be the same length. -If a character in the original string does not appear in the @from@ string, then it simply appears as is in the resulting string. -\begin{cfa} -// upper to lower case -name = name.translate( "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz" ); - // name is assigned "name" -s = ifstmt.translate( "ABCDEFGHIJKLMNOPQRSTUVWXYZ", "abcdefghijklmnopqrstuvwxyz" ); - // ifstmt is assigned "if (a > b) {" -// lower to upper case -name = name.translate( "abcdefghijklmnopqrstuvwxyz", "ABCDEFGHIJKLMNOPQRSTUVWXYZ" ); - // name is assigned "MIKE" -\end{cfa} - -The @replace@ operation -\begin{cfa} -string replace( string &from, string &to ) -\end{cfa} -returns a string in which all occurrences of the @from@ string in the current string have been replaced by the @to@ string. -\begin{cfa} -s = name.replace( "E", "XX" ); $\C{// s is assigned "PXXTXXR"}$ -\end{cfa} -The replacement is done left-to-right. -When an instance of the @from@ string is found and changed to the @to@ string, it is NOT examined again for further replacement. +\end{cfa} +\end{tabular} +\end{cquote} +The character-class operations indicates if a string is composed completely of a particular class of characters, \eg, alphabetic, numeric, vowels, \etc. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +charclass vowels{ "aeiouy" }; +i = include( "aaeiuyoo", vowels ); +i = include( "aabiuyoo", vowels ); +\end{cfa} +& +\begin{cfa} + +8 // compliant +2 // b non-compliant +\end{cfa} +\end{tabular} +\end{cquote} +@vowels@ defines a character class and function @include@ checks if all characters in the string are included in the class (compliance). +The position of the last character plus 1 is return if the string is compliant or the position of the first non-compliant character. +There is no relationship between the order of characters in the two strings. +Function @exclude@ is the reverse of @include@, checking if all characters in the string are excluded from the class (compliance). +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +i = exclude( "cdbfghmk", vowels ); +i = exclude( "cdyfghmk", vowels ); +\end{cfa} +& +\begin{cfa} +8 // compliant +2 // y non-compliant +\end{cfa} +\end{tabular} +\end{cquote} +Both forms can return the longest substring of compliant characters. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +s = include( "aaeiuyoo", vowels ); +s = include( "aabiuyoo", vowels ); +s = exclude( "cdbfghmk", vowels ); +s = exclude( "cdyfghmk", vowels ); +\end{cfa} +& +\begin{cfa} +"aaeiuyoo" +"aa" +"cdbfghmk" +"cd" +\end{cfa} +\end{tabular} +\end{cquote} + +The test operation checks if each character in a string is in one of the C character classes. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +i = test( "1FeC34aB", @isxdigit@ ); +i = test( ".,;'!\"", @ispunct@ ); +i = test( "XXXx", @isupper@ ); +\end{cfa} +& +\begin{cfa} +8 // compliant +6 // compliant +3 // non-compliant +\end{cfa} +\end{tabular} +\end{cquote} +The position of the last character plus 1 is return if the string is compliant or the position of the first non-compliant character. + +Combining substring and search allows actions like trimming whitespace from the start of a line. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +string line = " \t xxx yyy zzz"; +string trim = line( test( line, isspace ) ); +\end{cfa} +& +\begin{cfa} + +"xxx yyy zzz" +\end{cfa} +\end{tabular} +\end{cquote} + +The translate operation returns a string with each character transformed by one of the C character transformation functions. +\begin{cquote} +\setlength{\tabcolsep}{15pt} +\begin{tabular}{@{}l|l@{}} +\begin{cfa} +s = translate( "abc", @toupper@ ); +s = translate( "ABC", @tolower@ ); +int tospace( int c ) { return isspace( c ) ? ' ' : c; } +s = translate( "X X\tX\nX", @tospace@ ); +\end{cfa} +& +\begin{cfa} +"ABC" +"abc" + +"X X X X" +\end{cfa} +\end{tabular} +\end{cquote}