A rust macro that allows regular expression creation through independent files. Allows fully typed named groups.

using markdown file for docs

huncholaneauthored 1 year ago

parent 5423d78commit 4405def4b845c4dcd3c23ca0abb4b522e23ca5ffBrowse files

2 files changed, +383 -25

+382-0docs/load_regex_files.md

		@@ -0,0 +1,382 @@
	1	+# load_regex_files
	2	+
	3	+Loads a folder filled with regular expression files ending with `.re`.
	4	+
	5	+All regex files are loaded with the `m` and `x` flags.
	6	+
	7	+- `m` (multi-line): `^` and `$` match the start and end of lines, not just the entire input.
	8	+- `x` (extended): allows whitespace and comments starting with `#` inside the regex.
	9	+
	10	+## Event Example
	11	+
	12	+### regex/event.re
	13	+
	14	+ ```text
	15	+# This will create a struct called EventRE with the fields start, end, ampm, and activity
	16	+
	17	+# Get the start
	18	+^(?<start>\d{1,2}:\d{1,2})
	19	+.
	20	+# Get the end time
	21	+(?<end>\d{1,2}:\d{1,2})
	22	+\s{0,2}
	23	+
	24	+# Get the AM or PM after the times
	25	+(?<ampm>[AMPM]{2})
	26	+.
	27	+# Get the activity string
	28	+(?<activity>.+)
	29	+```
	30	+
	31	+### samples/events.txt
	32	+
	33	+```text
	34	+🧠 Focused Dev + Growth Schedule
	35	+
	36	+Time Activity
	37	+7:30–8:00 AM Wake up + hydrate + light stretch
	38	+8:00–8:45 AM Gym (weights or intervals)
	39	+9:00–9:30 AM Breakfast + cooldown + planning
	40	+9:30–12:00PM Deep coding (core project)
	41	+12:00–12:45PM Lunch + decompress
	42	+12:45–2:30PM Coding or meetings if needed
	43	+2:30–3:00 PM Break or walk
	44	+3:00–5:00 PM Learning block (Rust, AI, etc)
	45	+5:00–6:00 PM Chill / side project / cleanup
	46	+6:00–7:00 PM Dinner + relax
	47	+7:00–9:00 PM Optional: build/test/hack ideas
	48	+9:00–10:00 PM Wind down (read, steam room, etc)
	49	+10:00–10:30PM Journal + sleep prep
	50	+```
	51	+
	52	+### examples/event.rs
	53	+
	54	+```rust
	55	+use regex_folder_macro::load_regex_files;
	56	+
	57	+load_regex_files!("regex");
	58	+
	59	+fn main() {
	60	+ let events = EventRE::vec_from_file("samples/events.txt").unwrap();
	61	+ println!("{}", serde_json::to_string_pretty(&events).unwrap());
	62	+}
	63	+```
	64	+
	65	+### Results
	66	+
	67	+```json
	68	+[
	69	+ {
	70	+ "start_pos": 50,
	71	+ "end_pos": 98,
	72	+ "start": {
	73	+ "start_pos": 50,
	74	+ "end_pos": 54,
	75	+ "val": "7:30"
	76	+ },
	77	+ "end": {
	78	+ "start_pos": 57,
	79	+ "end_pos": 61,
	80	+ "val": "8:00"
	81	+ },
	82	+ "ampm": {
	83	+ "start_pos": 62,
	84	+ "end_pos": 64,
	85	+ "val": "AM"
	86	+ },
	87	+ "activity": {
	88	+ "start_pos": 65,
	89	+ "end_pos": 98,
	90	+ "val": "Wake up + hydrate + light stretch"
	91	+ }
	92	+ },
	93	+ {
	94	+ "start_pos": 99,
	95	+ "end_pos": 140,
	96	+ "start": {
	97	+ "start_pos": 99,
	98	+ "end_pos": 103,
	99	+ "val": "8:00"
	100	+ },
	101	+ "end": {
	102	+ "start_pos": 106,
	103	+ "end_pos": 110,
	104	+ "val": "8:45"
	105	+ },
	106	+ "ampm": {
	107	+ "start_pos": 111,
	108	+ "end_pos": 113,
	109	+ "val": "AM"
	110	+ },
	111	+ "activity": {
	112	+ "start_pos": 114,
	113	+ "end_pos": 140,
	114	+ "val": "Gym (weights or intervals)"
	115	+ }
	116	+ },
	117	+ {
	118	+ "start_pos": 141,
	119	+ "end_pos": 187,
	120	+ "start": {
	121	+ "start_pos": 141,
	122	+ "end_pos": 145,
	123	+ "val": "9:00"
	124	+ },
	125	+ "end": {
	126	+ "start_pos": 148,
	127	+ "end_pos": 152,
	128	+ "val": "9:30"
	129	+ },
	130	+ "ampm": {
	131	+ "start_pos": 153,
	132	+ "end_pos": 155,
	133	+ "val": "AM"
	134	+ },
	135	+ "activity": {
	136	+ "start_pos": 156,
	137	+ "end_pos": 187,
	138	+ "val": "Breakfast + cooldown + planning"
	139	+ }
	140	+ },
	141	+ {
	142	+ "start_pos": 188,
	143	+ "end_pos": 229,
	144	+ "start": {
	145	+ "start_pos": 188,
	146	+ "end_pos": 192,
	147	+ "val": "9:30"
	148	+ },
	149	+ "end": {
	150	+ "start_pos": 195,
	151	+ "end_pos": 200,
	152	+ "val": "12:00"
	153	+ },
	154	+ "ampm": {
	155	+ "start_pos": 200,
	156	+ "end_pos": 202,
	157	+ "val": "PM"
	158	+ },
	159	+ "activity": {
	160	+ "start_pos": 203,
	161	+ "end_pos": 229,
	162	+ "val": "Deep coding (core project)"
	163	+ }
	164	+ },
	165	+ {
	166	+ "start_pos": 230,
	167	+ "end_pos": 264,
	168	+ "start": {
	169	+ "start_pos": 230,
	170	+ "end_pos": 235,
	171	+ "val": "12:00"
	172	+ },
	173	+ "end": {
	174	+ "start_pos": 238,
	175	+ "end_pos": 243,
	176	+ "val": "12:45"
	177	+ },
	178	+ "ampm": {
	179	+ "start_pos": 243,
	180	+ "end_pos": 245,
	181	+ "val": "PM"
	182	+ },
	183	+ "activity": {
	184	+ "start_pos": 246,
	185	+ "end_pos": 264,
	186	+ "val": "Lunch + decompress"
	187	+ }
	188	+ },
	189	+ {
	190	+ "start_pos": 265,
	191	+ "end_pos": 308,
	192	+ "start": {
	193	+ "start_pos": 265,
	194	+ "end_pos": 270,
	195	+ "val": "12:45"
	196	+ },
	197	+ "end": {
	198	+ "start_pos": 273,
	199	+ "end_pos": 277,
	200	+ "val": "2:30"
	201	+ },
	202	+ "ampm": {
	203	+ "start_pos": 277,
	204	+ "end_pos": 279,
	205	+ "val": "PM"
	206	+ },
	207	+ "activity": {
	208	+ "start_pos": 280,
	209	+ "end_pos": 308,
	210	+ "val": "Coding or meetings if needed"
	211	+ }
	212	+ },
	213	+ {
	214	+ "start_pos": 309,
	215	+ "end_pos": 337,
	216	+ "start": {
	217	+ "start_pos": 309,
	218	+ "end_pos": 313,
	219	+ "val": "2:30"
	220	+ },
	221	+ "end": {
	222	+ "start_pos": 316,
	223	+ "end_pos": 320,
	224	+ "val": "3:00"
	225	+ },
	226	+ "ampm": {
	227	+ "start_pos": 321,
	228	+ "end_pos": 323,
	229	+ "val": "PM"
	230	+ },
	231	+ "activity": {
	232	+ "start_pos": 324,
	233	+ "end_pos": 337,
	234	+ "val": "Break or walk"
	235	+ }
	236	+ },
	237	+ {
	238	+ "start_pos": 338,
	239	+ "end_pos": 383,
	240	+ "start": {
	241	+ "start_pos": 338,
	242	+ "end_pos": 342,
	243	+ "val": "3:00"
	244	+ },
	245	+ "end": {
	246	+ "start_pos": 345,
	247	+ "end_pos": 349,
	248	+ "val": "5:00"
	249	+ },
	250	+ "ampm": {
	251	+ "start_pos": 350,
	252	+ "end_pos": 352,
	253	+ "val": "PM"
	254	+ },
	255	+ "activity": {
	256	+ "start_pos": 353,
	257	+ "end_pos": 383,
	258	+ "val": "Learning block (Rust, AI, etc)"
	259	+ }
	260	+ },
	261	+ {
	262	+ "start_pos": 384,
	263	+ "end_pos": 429,
	264	+ "start": {
	265	+ "start_pos": 384,
	266	+ "end_pos": 388,
	267	+ "val": "5:00"
	268	+ },
	269	+ "end": {
	270	+ "start_pos": 391,
	271	+ "end_pos": 395,
	272	+ "val": "6:00"
	273	+ },
	274	+ "ampm": {
	275	+ "start_pos": 396,
	276	+ "end_pos": 398,
	277	+ "val": "PM"
	278	+ },
	279	+ "activity": {
	280	+ "start_pos": 399,
	281	+ "end_pos": 429,
	282	+ "val": "Chill / side project / cleanup"
	283	+ }
	284	+ },
	285	+ {
	286	+ "start_pos": 430,
	287	+ "end_pos": 459,
	288	+ "start": {
	289	+ "start_pos": 430,
	290	+ "end_pos": 434,
	291	+ "val": "6:00"
	292	+ },
	293	+ "end": {
	294	+ "start_pos": 437,
	295	+ "end_pos": 441,
	296	+ "val": "7:00"
	297	+ },
	298	+ "ampm": {
	299	+ "start_pos": 442,
	300	+ "end_pos": 444,
	301	+ "val": "PM"
	302	+ },
	303	+ "activity": {
	304	+ "start_pos": 445,
	305	+ "end_pos": 459,
	306	+ "val": "Dinner + relax"
	307	+ }
	308	+ },
	309	+ {
	310	+ "start_pos": 460,
	311	+ "end_pos": 506,
	312	+ "start": {
	313	+ "start_pos": 460,
	314	+ "end_pos": 464,
	315	+ "val": "7:00"
	316	+ },
	317	+ "end": {
	318	+ "start_pos": 467,
	319	+ "end_pos": 471,
	320	+ "val": "9:00"
	321	+ },
	322	+ "ampm": {
	323	+ "start_pos": 472,
	324	+ "end_pos": 474,
	325	+ "val": "PM"
	326	+ },
	327	+ "activity": {
	328	+ "start_pos": 475,
	329	+ "end_pos": 506,
	330	+ "val": "Optional: build/test/hack ideas"
	331	+ }
	332	+ },
	333	+ {
	334	+ "start_pos": 507,
	335	+ "end_pos": 556,
	336	+ "start": {
	337	+ "start_pos": 507,
	338	+ "end_pos": 511,
	339	+ "val": "9:00"
	340	+ },
	341	+ "end": {
	342	+ "start_pos": 514,
	343	+ "end_pos": 519,
	344	+ "val": "10:00"
	345	+ },
	346	+ "ampm": {
	347	+ "start_pos": 520,
	348	+ "end_pos": 522,
	349	+ "val": "PM"
	350	+ },
	351	+ "activity": {
	352	+ "start_pos": 523,
	353	+ "end_pos": 556,
	354	+ "val": "Wind down (read, steam room, etc)"
	355	+ }
	356	+ },
	357	+ {
	358	+ "start_pos": 557,
	359	+ "end_pos": 593,
	360	+ "start": {
	361	+ "start_pos": 557,
	362	+ "end_pos": 562,
	363	+ "val": "10:00"
	364	+ },
	365	+ "end": {
	366	+ "start_pos": 565,
	367	+ "end_pos": 570,
	368	+ "val": "10:30"
	369	+ },
	370	+ "ampm": {
	371	+ "start_pos": 570,
	372	+ "end_pos": 572,
	373	+ "val": "PM"
	374	+ },
	375	+ "activity": {
	376	+ "start_pos": 573,
	377	+ "end_pos": 593,
	378	+ "val": "Journal + sleep prep"
	379	+ }
	380	+ }
	381	+]
	382	+```

+1-25src/lib.rs

		@@ -5,31 +5,7 @@ use std::fs;
5	5	use syn::{parse_macro_input, Ident, LitStr};
6	6
7	7	#[proc_macro]
8		-/// Loads a folder filled with regular expression files ending with `.re`.
9		-///
10		-/// All regex files are loaded with the `m` and `x` flags.
11		-///
12		-/// - `m` (multi-line): `^` and `$` match the start and end of lines, not just the entire input.
13		-/// - `x` (extended): allows whitespace and comments starting with `#` inside the regex.
14		-///
15		-/// Event Example:
16		-/// ```text
17		-/// ./
18		-/// # This will create a struct called EventRE with the fields start, end, ampm, and activity
19		-///
20		-/// # Get the start
21		-/// ^(?<start>\d{1,2}:\d{1,2})
22		-/// .
23		-/// # Get the end time
24		-/// (?<end>\d{1,2}:\d{1,2})
25		-/// \s{0,2}
26		-///
27		-/// # Get the AM or PM after the times
28		-/// (?<ampm>[AMPM]{2})
29		-/// .
30		-/// # Get the activity string
31		-/// (?<activity>.+)
32		-/// ```
	8	+#[doc = include_str!("../docs/load_regex_files.md")]
33	9	pub fn load_regex_files(input: TokenStream) -> TokenStream {
34	10	let folder_path = parse_macro_input!(input as LitStr).value();
35	11