@@ -9,3 +9,111 @@ export const pascalToUpperSnake = (str: string): string => {
99 . toUpperCase ( ) // Converts everything to uppercase
1010 . replace ( / ^ _ / , '' ) ; // Removes the initial underscore if it exists
1111} ;
12+
13+
14+ /**
15+ * An array of strings containing various special character patterns and names.
16+ * The strings in this array include names or identifiers preceded by
17+ * special characters such as dashes, question marks, or periods.
18+ * Some entries also contain only special characters or brace-like structures.
19+ */
20+ const specialChars = [
21+ '—Huggo' ,
22+ '?—Nick Riganas' ,
23+ '.—Rhino' ,
24+ '—Eric Johnson' ,
25+ '—Jwelch5742' ,
26+ '—yusufpiskin' ,
27+ '—Maths Jesperson' ,
28+ '—Mark Logan' ,
29+ '—Snow Leopard' ,
30+ '—Claudio Carvalho, Rio de Janeiro, Brazil' ,
31+ '—Johnny-the-Film-Sentinel-2187' ,
32+ '—grantss' ,
33+ '—Ed Stephan' ,
34+ '—filmfactsman' ,
35+ '—Col Needham' ,
36+ '—Tony Fontana' ,
37+ '—garykmcd' ,
38+ '—' ,
39+ '?—' ,
40+ '.—' ,
41+ '{}' ,
42+ ] ;
43+
44+
45+ /**
46+ * A regular expression pattern used for matching and validating email addresses.
47+ *
48+ * This pattern supports common email formats, where:
49+ * - The local part can contain alphanumeric characters, dots, underscores,
50+ * percent signs, plus signs, and hyphens.
51+ * - The domain part is structured as one or more labels separated by dots,
52+ * with each label containing alphanumeric characters or hyphens.
53+ * - The top-level domain must be at least two characters long and consist
54+ * only of alphabetic characters.
55+ *
56+ * Flags:
57+ * - The "g" flag enables global matching, allowing multiple occurrences
58+ * of email addresses to be matched in a single string.
59+ */
60+ const emailRegex = / \b [ a - z A - Z 0 - 9 ] [ a - z A - Z 0 - 9 . _ % + - ] * @ (?: [ a - z A - Z 0 - 9 - ] + \. ) + [ a - z A - Z ] { 2 , } \b / g;
61+
62+
63+ /**
64+ * Removes special characters from the given text string and returns the cleaned string.
65+ *
66+ * @param {string } text - The input string from which special characters will be removed.
67+ * @return {string } - The resulting string after special characters are removed.
68+ */
69+ function removeSpecialChars ( text : string ) : string {
70+ // Loop through the special characters and replace them with spaces
71+ for ( const char of specialChars ) {
72+ text = text . replace ( char , '' ) . trim ( ) ;
73+ }
74+ return text ;
75+ }
76+
77+ /**
78+ * Detects whether the given text contains a valid email address pattern.
79+ *
80+ * @param {string } text - The string to be checked for an email address.
81+ * @return {boolean } Returns `true` if the text contains a valid email address, otherwise `false`.
82+ */
83+ function detectEmail ( text : string ) : boolean {
84+ return emailRegex . test ( text ) ;
85+ }
86+
87+ /**
88+ * Removes an email address from the provided text string, if present.
89+ *
90+ * @param {string } text - The input string potentially containing an email address.
91+ * @return {string } The modified string with the email address removed and trimmed of extra spaces.
92+ */
93+ function removeEmail ( text : string ) : string {
94+ return text . replace ( emailRegex , '' ) . trim ( ) ;
95+ }
96+
97+ /**
98+ * Processes and trims extra content from a publication text, including special characters,
99+ * email addresses, and patterns at the end of the text.
100+ *
101+ * @param {string } text - The input string representing the publication content to be processed.
102+ * @returns {string } The processed and cleaned text after applying trimming rules.
103+ */
104+ export const trimPublicationContentExtraText = ( text : string ) : string => {
105+ const hasEmail = detectEmail ( text ) ;
106+
107+ if ( hasEmail ) {
108+ text = removeEmail ( text ) ;
109+ }
110+
111+ let cleanedText = removeSpecialChars ( text ) ;
112+
113+ // Verify if the last character is a period, if not, add one
114+ if ( ! cleanedText . endsWith ( '.' ) ) {
115+ cleanedText += '.' ;
116+ }
117+
118+ return `${ cleanedText } ;
119+ } ;
0 commit comments