interpret/src/scan_kjv.re.c

226 lines
9.2 KiB
C

/** @license 2022 Neil Edelman, distributed under the terms of the
[MIT License](https://opensource.org/licenses/MIT).
Scan journal entries for kjv references. */
#include "../src/journal.h"
#include "../src/kjv.h"
#include "../src/helper.h"
#include <inttypes.h> /* C99 */
#include <stdlib.h>
#include <stdio.h>
#include <assert.h>
#include <limits.h>
/*!conditions:re2c*/
static int scan(union date32 date, const char *const buffer,
struct kjv *const kj) {
const char *YYCURSOR, *YYMARKER, *yyt1, *yyt2, *yyt3, *s0, *s1, *t0, *t1;
enum kjv_book book = Revelation;
uint32_t chapter = 0, verse = 0, verse_end = 0;
enum YYCONDTYPE condition = yycline;
size_t line = 1;
char datestr[12] = {0};
const char *why = "unexpected";
assert(buffer && kj);
YYCURSOR = YYMARKER = yyt1 = buffer;
/*!re2c /**/
re2c:define:YYCTYPE = char;
re2c:yyfill:enable = 0;
re2c:define:YYGETCONDITION = "condition";
re2c:define:YYSETCONDITION = "condition = @@;";
re2c:define:YYGETCONDITION:naked = 1;
re2c:define:YYSETCONDITION:naked = 1;
unix_control = [\x01-\x08\x0a-\x1f\x7f];
ws = [ \t];
glyph = [^] \ ("\x00" | "\n" | unix_control | ws);
natural = [1-9][0-9]*;
engage = ws+ "--" ws+;
/* (natural ":")? Don't use for memorizing and use for reading, I think? */
/*("``"|"\"") This is not in the next book. */
lookat = ws* natural ":" natural [ab]? ("-" natural [ab]?)? engage;
first = ("I" | "1") " "?;
second = ("II" | "2") " "?;
third = ("III" | "3") " "?;
*/
for( ; ; ) { /*!re2c /**/
<skip> [^\n\x00] { continue; }
<skip> "\x00" { why = "no newline at end of file"; goto catch; }
<skip> "\n" => line { line++; continue; }
<line> "\x00" { return 1; }
<line> "\n" { line++; continue; }
<line> * :=> skip /* Guess it can't be simplified? */
<line> "Genesis" / lookat => book { book = Genesis; continue; }
<line> "Exodus" / lookat => book { book = Exodus; continue; }
<line> "Leviticus" / lookat => book { book = Leviticus; continue; }
<line> "Numbers" / lookat => book { book = Numbers; continue; }
<line> "Deuteronomy" / lookat => book { book = Deuteronomy; continue; }
<line> "Joshua" / lookat => book { book = Joshua; continue; }
<line> "Judges" / lookat => book { book = Judges; continue; }
<line> "Ruth" / lookat => book { book = Ruth; continue; }
<line> first "Samuel" / lookat => book { book = ISamuel; continue; }
<line> second "Samuel" / lookat => book { book = IISamuel; continue; }
<line> first "Kings" / lookat => book { book = IKings; continue; }
<line> second "Kings" / lookat => book { book = IIKings; continue; }
<line> first "Chronicles" / lookat
=> book { book = IChronicles; continue; }
<line> second "Chronicles" / lookat
=> book { book = IIChronicles; continue; }
<line> "Ezra" / lookat => book { book = Ezra; continue; }
<line> "Nehemiah" / lookat => book { book = Nehemiah; continue; }
<line> "Esther" / lookat => book { book = Esther; continue; }
<line> "Job" / lookat => book { book = Job; continue; }
<line> "Psalms" / lookat => book { book = Psalms; continue; }
<line> "Proverbs" / lookat => book { book = Proverbs; continue; }
<line> "Ecclesiastes" / lookat
=> book { book = Ecclesiastes; continue; }
<line> "Song of Solomon" / lookat
=> book { book = Song_of_Solomon; continue; }
<line> "Isaiah" / lookat => book { book = Isaiah; continue; }
<line> "Jeremiah" / lookat => book { book = Jeremiah; continue; }
<line> "Lamentations" / lookat
=> book { book = Lamentations; continue; }
<line> "Ezekiel" / lookat => book { book = Ezekiel; continue; }
<line> "Daniel" / lookat => book { book = Daniel; continue; }
<line> "Hosea" / lookat => book { book = Hosea; continue; }
<line> "Joel" / lookat => book { book = Joel; continue; }
<line> "Amos" / lookat => book { book = Amos; continue; }
<line> "Obadiah" / lookat => book { book = Obadiah; continue; }
<line> "Jonah" / lookat => book { book = Jonah; continue; }
<line> "Micah" / lookat => book { book = Micah; continue; }
<line> "Nahum" / lookat => book { book = Nahum; continue; }
<line> "Habakkuk" / lookat => book { book = Habakkuk; continue; }
<line> "Zephaniah" / lookat => book { book = Zephaniah; continue; }
<line> "Haggai" / lookat => book { book = Haggai; continue; }
<line> "Zechariah" / lookat => book { book = Zechariah; continue; }
<line> "Malachi" / lookat => book { book = Malachi; continue; }
<line> "Matthew" / lookat => book { book = Matthew; continue; }
<line> "Mark" / lookat => book { book = Mark; continue; }
<line> "Luke" / lookat => book { book = Luke; continue; }
<line> "John" / lookat => book { book = John; continue; }
<line> "Acts" / lookat => book { book = Acts; continue; }
<line> "Romans" / lookat => book { book = Romans; continue; }
<line> first "Corinthians" / lookat
=> book { book = ICorinthians; continue; }
<line> second "Corinthians" / lookat
=> book { book = IICorinthians; continue; }
<line> "Galatians" / lookat => book { book = Galatians; continue; }
<line> "Ephesians" / lookat => book { book = Ephesians; continue; }
<line> "Philippians" / lookat => book { book = Philippians; continue; }
<line> "Colossians" / lookat => book { book = Colossians; continue; }
<line> first "Thessalonians" / lookat
=> book { book = IThessalonians; continue; }
<line> second "Thessalonians" / lookat
=> book { book = IIThessalonians; continue; }
<line> first "Timothy" / lookat => book { book = ITimothy; continue; }
<line> second "Timothy" / lookat => book { book = IITimothy; continue; }
<line> "Titus" / lookat => book { book = Titus; continue; }
<line> "Philemon" / lookat => book { book = Philemon; continue; }
<line> "Hebrews" / lookat => book { book = Hebrews; continue; }
<line> "James" / lookat => book { book = James; continue; }
<line> first "Peter" / lookat => book { book = IPeter; continue; }
<line> second "Peter" / lookat => book { book = IIPeter; continue; }
<line> first "John" / lookat => book { book = IJohn; continue; }
<line> second "John" / lookat => book { book = IIJohn; continue; }
<line> third "John" / lookat => book { book = IIIJohn; continue; }
<line> "Jude" / lookat => book { book = Jude; continue; }
<line> "Revelation" / lookat => book { book = Revelation; continue; }
<book> * { why = "default unrecognized"; goto catch; }
/* 19:15a, just ignore the a. */
<book> ws+ @s0 natural @s1 ":" @t0 natural @t1 [ab]? {
if(chapter || verse || verse_end)
{ why = "reference unrecognized"; goto catch; }
if(!helper_natural(s0, s1, &chapter)
|| !helper_natural(t0, t1, &verse))
{ why = "reference numerical error"; goto catch; }
continue;
}
<book> "-" @s0 natural @s1 [ab]? { /* Verse range. */
if(!chapter || !verse || verse_end)
{ why = "range unrecognized"; goto catch; }
if(!helper_natural(s0, s1, &verse_end))
{ why = "range numerical error"; goto catch; }
continue;
}
<book> engage => skip {
char citestr[12];
if(!chapter || !verse) { why = "missing information"; goto catch; }
if(verse_end && verse_end <= verse)
{ why = "interval error"; goto catch; }
union kjvcite cite
= { .book = book, .chapter = chapter, .verse = verse };
if(!datestr[0]) date32_to_string(date, &datestr); /* Only once. */
kjvcite_to_string(cite, &citestr);
for( ; ; verse++, cite.verse++) {
if(!kjv_add(kj, cite)) { why = "add to set"; goto catch; }
if(!verse_end || verse_end <= verse) break;
}
printf("%s\t%zu\t%zu\t%zu\t# ",
datestr, kj->words.verse, kj->words.set, kj->words.cumulative);
if(verse_end) {
printf("%s-%" PRIu32 "\n", citestr, verse_end);
} else {
printf("%s\n", citestr);
}
book = Revelation, chapter = 0, verse = 0, verse_end = 0;
continue;
}
*/ }
assert(0); /* Never gets here. */
catch:
if(!errno) errno = EILSEQ;
date32_to_string(date, &datestr);
fprintf(stderr, "%s\n"
"%s line %zu: %s.\n", buffer, datestr, line, why);
return 0;
}
int main(void) {
int success = EXIT_SUCCESS;
struct journal j;
struct journal_iterator it;
struct kjv kj = kjv();
union date32 k;
union load *v;
size_t i;
/*scan((union date32){.year=2000, .month=1, .day=1}, "\n\n\n"
"Romans 3:23 -- ``For all have sinned, "
"and come short of the glory of God.''\n", &kj);*/
/* FIXME: have a column with the number so we can see how much uniqueness
makes a difference. */
j = journal();
if(!journal_is_valid(&j)) goto catch;
fprintf(stderr, "Journal: %s.\n", journal_to_string(&j));
printf("set term postscript eps enhanced\n"
"set output \"kjv.eps\"\n"
"$Data <<EOD\n"
"# date\tverse\tset\tcumulative / %zu\n", kj.words.total);
it = journal_begin(&j), i = 0; while(journal_next(&it, &k, &v)) {
if(!scan(k, v->text, &kj)) goto catch;
/*if(++i > 32) break;*/
}
printf("EOD\n"
"set monochrome\n"
"set xdata time\n"
"set timefmt \"%%Y-%%m-%%d\"\n"
"set xtics format \"%%Y-%%m-%%d\" rotate by -30\n"
"set ylabel \"words in KJV\"\n"
"set format y \"%%g%%%%\"\n"
"set key top left\n"
"set grid\n"
"unset border\n"
"#set style fill solid 0.1 #pattern 5 (better, but restarts)\n"
"plot $Data using 1:($3)*100/%zu with fillsteps lw 2 title \"set\", \\\n"
"$Data using 1:($4)*100/%zu with steps lw 1 title \"cumulative\"\n",
kj.words.total, kj.words.total);
goto finally;
catch:
success = EXIT_FAILURE;
perror("journal");
finally:
journal_(&j);
return success;
}