Deprecate JSON output format
This commit is contained in:
parent
faba716e87
commit
5a6d4e4b8b
4
Makefile
4
Makefile
@ -24,8 +24,8 @@ O=-O3
|
||||
ALL_FLAGS=$(CFLAGS) $(OSFLAGS) -DBP_NAME="\"$(NAME)\"" $(EXTRA) $(CWARN) $(G) $(O)
|
||||
|
||||
LIBFILE=lib$(NAME).so
|
||||
CFILES=pattern.c utils.c match.c files.c printmatch.c json.c utf8.c
|
||||
HFILES=files.h json.h match.h pattern.h printmatch.h utf8.h utils.h
|
||||
CFILES=pattern.c utils.c match.c files.c printmatch.c utf8.c
|
||||
HFILES=files.h match.h pattern.h printmatch.h utf8.h utils.h
|
||||
OBJFILES=$(CFILES:.c=.o)
|
||||
|
||||
$(NAME): $(OBJFILES) bp.c
|
||||
|
||||
@ -29,7 +29,6 @@ to and including the next occurrence of "baz" on the same line).
|
||||
* `-i` `--ignore-case` perform a case-insensitive match
|
||||
* `-I` `--inplace` perform replacements or filtering in-place on files
|
||||
* `-e` `--explain` print an explanation of the matches
|
||||
* `-j` `--json` print matches as JSON objects
|
||||
* `-l` `--list-files` print only filenames containing matches
|
||||
* `-r` `--replace <replacement>` replace the input pattern with the given replacement
|
||||
* `-s` `--skip <skip pattern>` skip over the given pattern when looking for matches
|
||||
@ -150,7 +149,6 @@ File | Description
|
||||
-------------------------------|-----------------------------------------------------
|
||||
[bp.c](bp.c) | The main program.
|
||||
[files.c](files.c) | Loading files into memory.
|
||||
[json.c](json.c) | JSON output of matches.
|
||||
[match.c](match.c) | Pattern matching code (find occurrences of a bp pattern within an input string).
|
||||
[pattern.c](pattern.c) | Pattern compiling code (compile a bp pattern from an input string).
|
||||
[printmatch.c](printmatch.c) | Printing a visual explanation of a match.
|
||||
|
||||
28
bp.1
28
bp.1
@ -1,30 +1,12 @@
|
||||
.\" Automatically generated by Pandoc 3.1.6
|
||||
.\" Automatically generated by Pandoc 3.1.8
|
||||
.\"
|
||||
.\" Define V font for inline verbatim, using C font in formats
|
||||
.\" that render this, and otherwise B font.
|
||||
.ie "\f[CB]x\f[]"x" \{\
|
||||
. ftr V B
|
||||
. ftr VI BI
|
||||
. ftr VB B
|
||||
. ftr VBI BI
|
||||
.\}
|
||||
.el \{\
|
||||
. ftr V CR
|
||||
. ftr VI CI
|
||||
. ftr VB CB
|
||||
. ftr VBI CBI
|
||||
.\}
|
||||
.TH "BP" "1" "May 17 2021" "" ""
|
||||
.hy
|
||||
.SH NAME
|
||||
.PP
|
||||
bp - Bruce\[aq]s Parsing Expression Grammar tool
|
||||
.SH SYNOPSIS
|
||||
.PP
|
||||
\f[B]bp\f[R] [\f[I]options\&...\f[R]] \f[I]pattern\f[R] [[\f[B]--\f[R]]
|
||||
\f[I]files\&...\f[R]]
|
||||
.SH DESCRIPTION
|
||||
.PP
|
||||
\f[B]bp\f[R] is a tool that matches parsing expression grammars using a
|
||||
custom syntax.
|
||||
.SH OPTIONS
|
||||
@ -42,10 +24,6 @@ Surround a string pattern with word boundaries (equivalent to \f[B]bp
|
||||
\f[B]-e\f[R], \f[B]--explain\f[R]
|
||||
Print a visual explanation of the matches.
|
||||
.TP
|
||||
\f[B]-j\f[R], \f[B]--json\f[R]
|
||||
Print a JSON list of the matches.
|
||||
(Pairs with \f[B]--verbose\f[R] for more detail)
|
||||
.TP
|
||||
\f[B]-l\f[R], \f[B]--list-files\f[R]
|
||||
Print only the names of files containing matches instead of the matches
|
||||
themselves.
|
||||
@ -115,7 +93,6 @@ used instead.
|
||||
If neither are provided, \f[B]bp\f[R] will search through all files in
|
||||
the current directory and its subdirectories (recursively).
|
||||
.SH STRING PATTERNS
|
||||
.PP
|
||||
One of the most common use cases for pattern matching tools is matching
|
||||
plain, literal strings, or strings that are primarily plain strings,
|
||||
with one or two patterns.
|
||||
@ -132,7 +109,6 @@ character literal: \f[B]{\[ga]{}\f[R], the string literal:
|
||||
\f[B]{\[dq]{\[dq]}\f[R], or a pair of matching curly braces using the
|
||||
\f[B]braces\f[R] rule: \f[B]{braces}\f[R].
|
||||
.SH PATTERNS
|
||||
.PP
|
||||
\f[B]bp\f[R] patterns are based off of a combination of Parsing
|
||||
Expression Grammars and regular expression syntax.
|
||||
The syntax is designed to map closely to verbal descriptions of the
|
||||
@ -377,7 +353,6 @@ that also attaches a metadata tag of the same name)
|
||||
\f[B]#\f[R] \f[I]comment\f[R]
|
||||
A line comment, ignored by BP
|
||||
.SH GRAMMAR FILES
|
||||
.PP
|
||||
\f[B]bp\f[R] allows loading extra grammar files, which define patterns
|
||||
which may be used for matching.
|
||||
The \f[B]builtins\f[R] grammar file is loaded by default, and it defines
|
||||
@ -430,7 +405,6 @@ following command:
|
||||
\f[B]bp -g c++ \[aq]{comment \[ti] \[dq]TODO\[dq]}\[aq] *.cpp\f[R]
|
||||
.RE
|
||||
.SH EXAMPLES
|
||||
.PP
|
||||
Find files containing the literal string \[lq]foo.baz\[rq] (a string
|
||||
pattern):
|
||||
.RS
|
||||
|
||||
3
bp.1.md
3
bp.1.md
@ -27,9 +27,6 @@ syntax.
|
||||
`-e`, `--explain`
|
||||
: Print a visual explanation of the matches.
|
||||
|
||||
`-j`, `--json`
|
||||
: Print a JSON list of the matches. (Pairs with `--verbose` for more detail)
|
||||
|
||||
`-l`, `--list-files`
|
||||
: Print only the names of files containing matches instead of the matches
|
||||
themselves.
|
||||
|
||||
26
bp.c
26
bp.c
@ -22,7 +22,6 @@
|
||||
#include <unistd.h>
|
||||
|
||||
#include "files.h"
|
||||
#include "json.h"
|
||||
#include "match.h"
|
||||
#include "pattern.h"
|
||||
#include "printmatch.h"
|
||||
@ -40,7 +39,6 @@ static const char *usage = (
|
||||
" -h --help print the usage and quit\n"
|
||||
" -v --verbose print verbose debugging info\n"
|
||||
" -e --explain explain the matches\n"
|
||||
" -j --json print matches as a list of JSON objects\n"
|
||||
" -c --case use case sensitivity\n"
|
||||
" -i --ignore-case preform matching case-insensitively\n"
|
||||
" -I --inplace modify a file in-place\n"
|
||||
@ -65,7 +63,7 @@ static const char *usage = (
|
||||
static struct {
|
||||
int context_before, context_after;
|
||||
bool ignorecase, verbose, git_mode, print_filenames;
|
||||
enum { MODE_NORMAL, MODE_LISTFILES, MODE_INPLACE, MODE_JSON, MODE_EXPLAIN } mode;
|
||||
enum { MODE_NORMAL, MODE_LISTFILES, MODE_INPLACE, MODE_EXPLAIN } mode;
|
||||
enum { FORMAT_AUTO, FORMAT_FANCY, FORMAT_PLAIN, FORMAT_BARE, FORMAT_FILE_LINE } format;
|
||||
bp_pat_t *skip;
|
||||
} options = {
|
||||
@ -205,22 +203,6 @@ static int is_text_file(const char *filename)
|
||||
return 1;
|
||||
}
|
||||
|
||||
//
|
||||
// Print matches in JSON format.
|
||||
//
|
||||
static int print_matches_as_json(file_t *f, bp_pat_t *pattern, bp_pat_t *defs)
|
||||
{
|
||||
int nmatches = 0;
|
||||
for (bp_match_t *m = NULL; next_match(&m, f->start, f->end, pattern, defs, options.skip, options.ignorecase); ) {
|
||||
if (++nmatches > 1)
|
||||
printf(",\n");
|
||||
printf("{\"filename\":\"%s\",\"match\":", f->filename);
|
||||
json_match(f->start, m, options.verbose);
|
||||
printf("}");
|
||||
}
|
||||
return nmatches;
|
||||
}
|
||||
|
||||
//
|
||||
// Print matches in a visual explanation style
|
||||
//
|
||||
@ -418,8 +400,6 @@ static int process_file(const char *filename, bp_pat_t *pattern, bp_pat_t *defs)
|
||||
matches += 1;
|
||||
}
|
||||
stop_matching(&m);
|
||||
} else if (options.mode == MODE_JSON) {
|
||||
matches += print_matches_as_json(f, pattern, defs);
|
||||
} else if (options.mode == MODE_INPLACE) {
|
||||
bp_match_t *m = NULL;
|
||||
bool found = next_match(&m, f->start, f->end, pattern, defs, options.skip, options.ignorecase);
|
||||
@ -586,8 +566,6 @@ int main(int argc, char *argv[])
|
||||
options.verbose = true;
|
||||
} else if (BOOLFLAG("-e") || BOOLFLAG("--explain")) {
|
||||
options.mode = MODE_EXPLAIN;
|
||||
} else if (BOOLFLAG("-j") || BOOLFLAG("--json")) {
|
||||
options.mode = MODE_JSON;
|
||||
} else if (BOOLFLAG("-I") || BOOLFLAG("--inplace")) {
|
||||
options.mode = MODE_INPLACE;
|
||||
options.print_filenames = false;
|
||||
@ -686,7 +664,6 @@ int main(int argc, char *argv[])
|
||||
printf("Matching pattern: %P\n", pattern);
|
||||
|
||||
int found = 0;
|
||||
if (options.mode == MODE_JSON) printf("[");
|
||||
if (options.git_mode) { // Get the list of files from `git --ls-files ...`
|
||||
found = process_git_files(pattern, defs, argc, argv);
|
||||
} else if (argv[0]) {
|
||||
@ -708,7 +685,6 @@ int main(int argc, char *argv[])
|
||||
options.print_filenames = false; // Don't print filename on stdin
|
||||
found += process_file("", pattern, defs);
|
||||
}
|
||||
if (options.mode == MODE_JSON) printf("]\n");
|
||||
|
||||
// This code frees up all residual heap-allocated memory. Since the program
|
||||
// is about to exit, this step is unnecessary. However, it is useful for
|
||||
|
||||
86
json.c
86
json.c
@ -1,86 +0,0 @@
|
||||
//
|
||||
// json.c - Code for printing JSON output of matches.
|
||||
//
|
||||
|
||||
#include <stdio.h>
|
||||
|
||||
#include "json.h"
|
||||
#include "utils.h"
|
||||
|
||||
__attribute__((nonnull))
|
||||
static int _json_match(const char *text, bp_match_t *m, int comma, bool verbose);
|
||||
|
||||
//
|
||||
// Helper function for json_match().
|
||||
// `comma` is used to track whether a comma will need to be printed before the
|
||||
// next object or not.
|
||||
//
|
||||
static int _json_match(const char *text, bp_match_t *m, int comma, bool verbose)
|
||||
{
|
||||
if (!verbose && m->pat->type != BP_TAGGED) {
|
||||
if (m->children) {
|
||||
for (int i = 0; m->children && m->children[i]; i++)
|
||||
comma |= _json_match(text, m->children[i], comma, verbose);
|
||||
}
|
||||
return comma;
|
||||
}
|
||||
|
||||
if (comma) printf(",\n");
|
||||
comma = 0;
|
||||
printf("{");
|
||||
if (m->pat->type == BP_TAGGED) {
|
||||
printf("\"tag\":\"%.*s\"", (int)When(m->pat, BP_TAGGED)->namelen, When(m->pat, BP_TAGGED)->name);
|
||||
comma = 1;
|
||||
}
|
||||
if (verbose) {
|
||||
if (comma) printf(",");
|
||||
printf("\"rule\":\"");
|
||||
for (const char *c = m->pat->start; c < m->pat->end; c++) {
|
||||
switch (*c) {
|
||||
case '"': printf("\\\""); break;
|
||||
case '\\': printf("\\\\"); break;
|
||||
case '\t': printf("\\t"); break;
|
||||
case '\n': printf("↵"); break;
|
||||
default: printf("%c", *c); break;
|
||||
}
|
||||
}
|
||||
printf("\",");
|
||||
printf("\"range\":[%zd,%zd]", m->start - text, m->end - text);
|
||||
comma = 1;
|
||||
} else {
|
||||
if (comma) printf(",");
|
||||
printf("\"text\":\"");
|
||||
for (const char *c = m->start; c < m->end; c++) {
|
||||
switch (*c) {
|
||||
case '"': printf("\\\""); break;
|
||||
case '\\': printf("\\\\"); break;
|
||||
case '\t': printf("\\t"); break;
|
||||
case '\n': printf("↵"); break;
|
||||
default: printf("%c", *c); break;
|
||||
}
|
||||
}
|
||||
printf("\"");
|
||||
comma = 1;
|
||||
}
|
||||
|
||||
if (m->children) {
|
||||
if (comma) printf(",");
|
||||
printf("\"children\":[");
|
||||
comma = 0;
|
||||
for (int i = 0; m->children && m->children[i]; i++)
|
||||
comma |= _json_match(text, m->children[i], comma, verbose);
|
||||
printf("]");
|
||||
}
|
||||
printf("}");
|
||||
return 1;
|
||||
}
|
||||
|
||||
//
|
||||
// Print a match object as a JSON object.
|
||||
//
|
||||
public void json_match(const char *text, bp_match_t *m, bool verbose)
|
||||
{
|
||||
(void)_json_match(text, m, 0, verbose);
|
||||
}
|
||||
|
||||
// vim: ts=4 sw=0 et cino=L2,l1,(0,W4,m1,\:0
|
||||
Loading…
Reference in New Issue
Block a user