mirror of https://github.com/eleith/emailjs.git
smtp/address: refactor
This commit is contained in:
parent
9b2a2e15e6
commit
a1b317e74b
309
smtp/address.ts
309
smtp/address.ts
|
@ -1,23 +1,4 @@
|
||||||
/*
|
interface AddressToken {
|
||||||
* Operator tokens and which tokens are expected to end the sequence
|
|
||||||
*/
|
|
||||||
const OPERATORS = {
|
|
||||||
'"': '"',
|
|
||||||
'(': ')',
|
|
||||||
'<': '>',
|
|
||||||
',': '',
|
|
||||||
// Groups are ended by semicolons
|
|
||||||
':': ';',
|
|
||||||
// Semicolons are not a legal delimiter per the RFC2822 grammar other
|
|
||||||
// than for terminating a group, but they are also not valid for any
|
|
||||||
// other use in this context. Given that some mail clients have
|
|
||||||
// historically allowed the semicolon as a delimiter equivalent to the
|
|
||||||
// comma in their UI, it makes sense to treat them the same as a comma
|
|
||||||
// when used outside of a group.
|
|
||||||
';': '',
|
|
||||||
};
|
|
||||||
|
|
||||||
interface TokenizerNode {
|
|
||||||
type: 'operator' | 'text';
|
type: 'operator' | 'text';
|
||||||
value: string;
|
value: string;
|
||||||
}
|
}
|
||||||
|
@ -28,134 +9,79 @@ export interface AddressObject {
|
||||||
group?: AddressObject[];
|
group?: AddressObject[];
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/*
|
||||||
* Creates a Tokenizer object for tokenizing address field strings
|
* Operator tokens and which tokens are expected to end the sequence
|
||||||
*
|
|
||||||
* @constructor
|
|
||||||
* @param {String} str Address field string
|
|
||||||
*/
|
*/
|
||||||
class Tokenizer {
|
const OPERATORS = new Map([
|
||||||
private operatorExpecting = '';
|
['"', '"'],
|
||||||
private node?: TokenizerNode;
|
['(', ')'],
|
||||||
private escaped = false;
|
['<', '>'],
|
||||||
private list: TokenizerNode[] = [];
|
[',', ''],
|
||||||
private str: string;
|
// Groups are ended by semicolons
|
||||||
|
[':', ';'],
|
||||||
|
// Semicolons are not a legal delimiter per the RFC2822 grammar other
|
||||||
|
// than for terminating a group, but they are also not valid for any
|
||||||
|
// other use in this context. Given that some mail clients have
|
||||||
|
// historically allowed the semicolon as a delimiter equivalent to the
|
||||||
|
// comma in their UI, it makes sense to treat them the same as a comma
|
||||||
|
// when used outside of a group.
|
||||||
|
[';', ''],
|
||||||
|
]);
|
||||||
|
|
||||||
constructor(str: string | string[] = '') {
|
/**
|
||||||
this.str = str.toString();
|
* Tokenizes the original input string
|
||||||
}
|
*
|
||||||
|
* @param {string | string[] | undefined} address string(s) to tokenize
|
||||||
|
* @return {AddressToken[]} An array of operator|text tokens
|
||||||
|
*/
|
||||||
|
function tokenizeAddress(address: string | string[] = '') {
|
||||||
|
const tokens: AddressToken[] = [];
|
||||||
|
let token: AddressToken | undefined = undefined;
|
||||||
|
let operator: string | undefined = undefined;
|
||||||
|
|
||||||
/**
|
for (const character of address.toString()) {
|
||||||
* Tokenizes the original input string
|
if ((operator?.length ?? 0) > 0 && character === operator) {
|
||||||
*
|
tokens.push({ type: 'operator', value: character });
|
||||||
* @return {Array} An array of operator|text tokens
|
token = undefined;
|
||||||
*/
|
operator = undefined;
|
||||||
public tokenize() {
|
} else if ((operator?.length ?? 0) === 0 && OPERATORS.has(character)) {
|
||||||
let chr;
|
tokens.push({ type: 'operator', value: character });
|
||||||
const list: TokenizerNode[] = [];
|
token = undefined;
|
||||||
|
operator = OPERATORS.get(character);
|
||||||
for (let i = 0, len = this.str.length; i < len; i++) {
|
} else {
|
||||||
chr = this.str.charAt(i);
|
if (token == null) {
|
||||||
this.checkChar(chr);
|
token = { type: 'text', value: character };
|
||||||
}
|
tokens.push(token);
|
||||||
|
} else {
|
||||||
for (const node of this.list) {
|
token.value += character;
|
||||||
node.value = (node.value || '').toString().trim();
|
|
||||||
if (node.value) {
|
|
||||||
list.push(node);
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return list;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
return tokens
|
||||||
* Checks if a character is an operator or text and acts accordingly
|
.map((x) => {
|
||||||
*
|
x.value = x.value.trim();
|
||||||
* @param {string} chr Character from the address field
|
return x;
|
||||||
* @returns {void}
|
})
|
||||||
*/
|
.filter((x) => x.value.length > 0);
|
||||||
public checkChar(chr: string) {
|
|
||||||
if ((chr in OPERATORS || chr === '\\') && this.escaped) {
|
|
||||||
this.escaped = false;
|
|
||||||
} else if (this.operatorExpecting && chr === this.operatorExpecting) {
|
|
||||||
this.node = {
|
|
||||||
type: 'operator',
|
|
||||||
value: chr,
|
|
||||||
};
|
|
||||||
this.list.push(this.node);
|
|
||||||
this.node = undefined;
|
|
||||||
this.operatorExpecting = '';
|
|
||||||
this.escaped = false;
|
|
||||||
return;
|
|
||||||
} else if (!this.operatorExpecting && chr in OPERATORS) {
|
|
||||||
this.node = {
|
|
||||||
type: 'operator',
|
|
||||||
value: chr,
|
|
||||||
};
|
|
||||||
this.list.push(this.node);
|
|
||||||
this.node = undefined;
|
|
||||||
this.operatorExpecting = OPERATORS[chr as keyof typeof OPERATORS];
|
|
||||||
this.escaped = false;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!this.escaped && chr === '\\') {
|
|
||||||
this.escaped = true;
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (!this.node) {
|
|
||||||
this.node = {
|
|
||||||
type: 'text',
|
|
||||||
value: '',
|
|
||||||
};
|
|
||||||
this.list.push(this.node);
|
|
||||||
}
|
|
||||||
|
|
||||||
if (this.escaped && chr !== '\\') {
|
|
||||||
this.node.value += '\\';
|
|
||||||
}
|
|
||||||
|
|
||||||
this.node.value += chr;
|
|
||||||
this.escaped = false;
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Converts tokens for a single address into an address object
|
* Converts tokens for a single address into an address object
|
||||||
*
|
*
|
||||||
* @param {TokenizerNode[]} tokens Tokens object
|
* @param {AddressToken[]} tokens Tokens object
|
||||||
* @return {AddressObject[]} addresses object array
|
* @return {AddressObject[]} addresses object array
|
||||||
*/
|
*/
|
||||||
function handleAddress(tokens: TokenizerNode[]) {
|
function convertAddressTokens(tokens: AddressToken[]) {
|
||||||
let isGroup = false;
|
const addressObjects: AddressObject[] = [];
|
||||||
let state = 'text';
|
const groups: string[] = [];
|
||||||
|
|
||||||
let address: AddressObject;
|
|
||||||
|
|
||||||
let addresses: string[] = [];
|
let addresses: string[] = [];
|
||||||
let comments: string[] = [];
|
let comments: string[] = [];
|
||||||
let texts: string[] = [];
|
let texts: string[] = [];
|
||||||
|
|
||||||
const groups: string[] = [];
|
let state = 'text';
|
||||||
const addressObjects: AddressObject[] = [];
|
let isGroup = false;
|
||||||
|
function handleToken(token: AddressToken) {
|
||||||
const data: {
|
|
||||||
address: string;
|
|
||||||
comment: string;
|
|
||||||
group: string;
|
|
||||||
text: string;
|
|
||||||
} = {
|
|
||||||
address: '',
|
|
||||||
comment: '',
|
|
||||||
group: '',
|
|
||||||
text: '',
|
|
||||||
};
|
|
||||||
|
|
||||||
// Filter out <addresses>, (comments) and regular text
|
|
||||||
for (let i = 0, len = tokens.length; i < len; i++) {
|
|
||||||
const token = tokens[i];
|
|
||||||
|
|
||||||
if (token.type === 'operator') {
|
if (token.type === 'operator') {
|
||||||
switch (token.value) {
|
switch (token.value) {
|
||||||
case '<':
|
case '<':
|
||||||
|
@ -172,37 +98,39 @@ function handleAddress(tokens: TokenizerNode[]) {
|
||||||
state = 'text';
|
state = 'text';
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
} else {
|
} else if (token.value.length > 0) {
|
||||||
if (token.value) {
|
switch (state) {
|
||||||
switch (state) {
|
case 'address':
|
||||||
case 'address':
|
addresses.push(token.value);
|
||||||
addresses.push(token.value);
|
break;
|
||||||
break;
|
case 'comment':
|
||||||
case 'comment':
|
comments.push(token.value);
|
||||||
comments.push(token.value);
|
break;
|
||||||
break;
|
case 'group':
|
||||||
case 'group':
|
groups.push(token.value);
|
||||||
groups.push(token.value);
|
break;
|
||||||
break;
|
default:
|
||||||
default:
|
texts.push(token.value);
|
||||||
texts.push(token.value);
|
break;
|
||||||
break;
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Filter out <addresses>, (comments) and regular text
|
||||||
|
for (const token of tokens) {
|
||||||
|
handleToken(token);
|
||||||
|
}
|
||||||
|
|
||||||
// If there is no text but a comment, replace the two
|
// If there is no text but a comment, replace the two
|
||||||
if (texts.length === 0 && comments.length > 0) {
|
if (texts.length === 0 && comments.length > 0) {
|
||||||
texts = [...comments];
|
texts = [...comments];
|
||||||
comments = [];
|
comments = [];
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// http://tools.ietf.org/html/rfc2822#appendix-A.1.3
|
||||||
if (isGroup) {
|
if (isGroup) {
|
||||||
// http://tools.ietf.org/html/rfc2822#appendix-A.1.3
|
|
||||||
data.text = texts.join(' ');
|
|
||||||
addressObjects.push({
|
addressObjects.push({
|
||||||
name: data.text || undefined,
|
name: texts.length === 0 ? undefined : texts.join(' '),
|
||||||
group: groups.length > 0 ? addressparser(groups.join(',')) : [],
|
group: groups.length > 0 ? addressparser(groups.join(',')) : [],
|
||||||
});
|
});
|
||||||
} else {
|
} else {
|
||||||
|
@ -215,22 +143,21 @@ function handleAddress(tokens: TokenizerNode[]) {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
const _regexHandler = function (address: string) {
|
|
||||||
if (addresses.length === 0) {
|
|
||||||
addresses = [address.trim()];
|
|
||||||
return ' ';
|
|
||||||
} else {
|
|
||||||
return address;
|
|
||||||
}
|
|
||||||
};
|
|
||||||
|
|
||||||
// still no address
|
// still no address
|
||||||
if (addresses.length === 0) {
|
if (addresses.length === 0) {
|
||||||
for (let i = texts.length - 1; i >= 0; i--) {
|
for (let i = texts.length - 1; i >= 0; i--) {
|
||||||
texts[i] = texts[i]
|
texts[i] = texts[i]
|
||||||
.replace(/\s*\b[^@\s]+@[^@\s]+\b\s*/, _regexHandler)
|
.replace(/\s*\b[^@\s]+@[^@\s]+\b\s*/, (address: string) => {
|
||||||
|
if (addresses.length === 0) {
|
||||||
|
addresses = [address.trim()];
|
||||||
|
return ' ';
|
||||||
|
} else {
|
||||||
|
return address;
|
||||||
|
}
|
||||||
|
})
|
||||||
.trim();
|
.trim();
|
||||||
if (addresses.length) {
|
|
||||||
|
if (addresses.length > 0) {
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -245,30 +172,25 @@ function handleAddress(tokens: TokenizerNode[]) {
|
||||||
|
|
||||||
// Keep only the first address occurence, push others to regular text
|
// Keep only the first address occurence, push others to regular text
|
||||||
if (addresses.length > 1) {
|
if (addresses.length > 1) {
|
||||||
texts = texts.concat(addresses.splice(1));
|
texts = [...texts, ...addresses.splice(1)];
|
||||||
}
|
}
|
||||||
|
|
||||||
// Join values with spaces
|
if (addresses.length === 0 && isGroup) {
|
||||||
data.text = texts.join(' ');
|
|
||||||
data.address = addresses.join(' ');
|
|
||||||
|
|
||||||
if (!data.address && isGroup) {
|
|
||||||
return [];
|
return [];
|
||||||
} else {
|
} else {
|
||||||
address = {
|
// Join values with spaces
|
||||||
address: data.address || data.text || '',
|
let address = addresses.join(' ');
|
||||||
name: data.text || data.address || '',
|
let name = texts.length === 0 ? address : texts.join(' ');
|
||||||
};
|
|
||||||
|
|
||||||
if (address.address === address.name) {
|
if (address === name) {
|
||||||
if ((address.address || '').match(/@/)) {
|
if (address.match(/@/)) {
|
||||||
address.name = '';
|
name = '';
|
||||||
} else {
|
} else {
|
||||||
address.address = '';
|
address = '';
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
addressObjects.push(address);
|
addressObjects.push({ address, name });
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -286,41 +208,30 @@ function handleAddress(tokens: TokenizerNode[]) {
|
||||||
*
|
*
|
||||||
* [{name: "Name", address: "address@domain"}]
|
* [{name: "Name", address: "address@domain"}]
|
||||||
*
|
*
|
||||||
* @param {string} str Address field
|
* @param {string | string[] | undefined} address Address field
|
||||||
* @return {AddressObject[]} An array of address objects
|
* @return {AddressObject[]} An array of address objects
|
||||||
*/
|
*/
|
||||||
export function addressparser(str?: string | string[]) {
|
export function addressparser(address?: string | string[]) {
|
||||||
const tokenizer = new Tokenizer(str);
|
const addresses: AddressObject[] = [];
|
||||||
const tokens = tokenizer.tokenize();
|
let tokens: AddressToken[] = [];
|
||||||
|
|
||||||
const addresses: TokenizerNode[][] = [];
|
for (const token of tokenizeAddress(address)) {
|
||||||
let address: TokenizerNode[] = [];
|
|
||||||
let parsedAddresses: AddressObject[] = [];
|
|
||||||
|
|
||||||
for (const token of tokens) {
|
|
||||||
if (
|
if (
|
||||||
token.type === 'operator' &&
|
token.type === 'operator' &&
|
||||||
(token.value === ',' || token.value === ';')
|
(token.value === ',' || token.value === ';')
|
||||||
) {
|
) {
|
||||||
if (address.length) {
|
if (tokens.length > 0) {
|
||||||
addresses.push(address);
|
addresses.push(...convertAddressTokens(tokens));
|
||||||
}
|
}
|
||||||
address = [];
|
tokens = [];
|
||||||
} else {
|
} else {
|
||||||
address.push(token);
|
tokens.push(token);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if (address.length) {
|
if (tokens.length > 0) {
|
||||||
addresses.push(address);
|
addresses.push(...convertAddressTokens(tokens));
|
||||||
}
|
}
|
||||||
|
|
||||||
for (const address of addresses) {
|
return addresses;
|
||||||
const handled = handleAddress(address);
|
|
||||||
if (handled.length) {
|
|
||||||
parsedAddresses = parsedAddresses.concat(handled);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
return parsedAddresses;
|
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue