commit cf1a6751aaca3dbb6c8acd16c3d24e917788ee5c
parent 60f4a6c5a5514a61dcbef6ee1ea102be5c669730
Author: Nathaniel Chappelle <nathaniel@chappelle.dev>
Date: Sat, 24 Jan 2026 14:26:18 -0800
bringing over json, jsmn, and piping glue
Diffstat:
| M | .gitignore | | | 2 | ++ |
| A | Makefile | | | 21 | +++++++++++++++++++++ |
| A | jsmn.h | | | 473 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | json.c | | | 137 | +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ |
| A | json.h | | | 8 | ++++++++ |
| A | stamail.c | | | 30 | ++++++++++++++++++++++++++++++ |
6 files changed, 671 insertions(+), 0 deletions(-)
diff --git a/.gitignore b/.gitignore
@@ -1,2 +1,4 @@
test/
PROJECT
+*.o
+stamail
diff --git a/Makefile b/Makefile
@@ -0,0 +1,21 @@
+CC = cc
+CFLAGS = -std=c99 -Wall -Wextra -O2
+OBJ = stamail.o json.o
+BIN = stamail
+
+all: $(BIN)
+
+$(BIN): $(OBJ)
+ $(CC) $(CFLAGS) -o $@ $(OBJ)
+
+stamail.o: stamail.c json.h
+ $(CC) $(CFLAGS) -c stamail.c
+
+json.o: json.c json.h jsmn.h
+ $(CC) $(CFLAGS) -c json.c
+
+clean:
+ rm -f $(OBJ) $(BIN)
+
+.PHONY: all clean
+
diff --git a/jsmn.h b/jsmn.h
@@ -0,0 +1,473 @@
+/*
+ * jsmn, a minimalistic JSON parser in C.
+ *
+ * MIT License
+ *
+ * Copyright (c) 2010 Serge Zaitsev
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef JSMN_H
+#define JSMN_H
+
+#include <stddef.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef JSMN_STATIC
+#define JSMN_API static
+#else
+#define JSMN_API extern
+#endif
+
+/**
+ * JSON type identifier. Basic types are:
+ * o Object
+ * o Array
+ * o String
+ * o Other primitive: number, boolean (true/false) or null
+ */
+typedef enum {
+ JSMN_UNDEFINED = 0,
+ JSMN_OBJECT = 1 << 0,
+ JSMN_ARRAY = 1 << 1,
+ JSMN_STRING = 1 << 2,
+ JSMN_PRIMITIVE = 1 << 3
+} jsmntype_t;
+
+enum jsmnerr {
+ /* Not enough tokens were provided */
+ JSMN_ERROR_NOMEM = -1,
+ /* Invalid character inside JSON string */
+ JSMN_ERROR_INVAL = -2,
+ /* The string is not a full JSON packet, more bytes expected */
+ JSMN_ERROR_PART = -3
+};
+
+/**
+ * JSON token description.
+ * type type (object, array, string etc.)
+ * start start position in JSON data string
+ * end end position in JSON data string
+ */
+typedef struct jsmntok {
+ jsmntype_t type;
+ int start;
+ int end;
+ int size;
+#ifdef JSMN_PARENT_LINKS
+ int parent;
+#endif
+} jsmntok_t;
+
+/**
+ * JSON parser. Contains an array of token blocks available. Also stores
+ * the string being parsed now and current position in that string.
+ */
+typedef struct jsmn_parser {
+ unsigned int pos; /* offset in the JSON string */
+ unsigned int toknext; /* next token to allocate */
+ int toksuper; /* superior token node, e.g. parent object or array */
+} jsmn_parser;
+
+/**
+ * Create JSON parser over an array of tokens
+ */
+JSMN_API void jsmn_init(jsmn_parser *parser);
+
+/**
+ * Run JSON parser. It parses a JSON data string into and array of tokens, each
+ * describing
+ * a single JSON object.
+ */
+JSMN_API int jsmn_parse(jsmn_parser *parser, const char *js, const size_t len,
+ jsmntok_t *tokens, const unsigned int num_tokens);
+
+#ifndef JSMN_HEADER
+/**
+ * Allocates a fresh unused token from the token pool.
+ */
+static jsmntok_t *jsmn_alloc_token(jsmn_parser *parser, jsmntok_t *tokens,
+ const size_t num_tokens) {
+ jsmntok_t *tok;
+ if (parser->toknext >= num_tokens) {
+ return NULL;
+ }
+ tok = &tokens[parser->toknext++];
+ tok->start = tok->end = -1;
+ tok->size = 0;
+#ifdef JSMN_PARENT_LINKS
+ tok->parent = -1;
+#endif
+ return tok;
+}
+
+/**
+ * Fills token type and boundaries.
+ */
+static void jsmn_fill_token(jsmntok_t *token, const jsmntype_t type,
+ const int start, const int end) {
+ token->type = type;
+ token->start = start;
+ token->end = end;
+ token->size = 0;
+}
+
+/**
+ * Fills next available token with JSON primitive.
+ */
+static int jsmn_parse_primitive(jsmn_parser *parser, const char *js,
+ const size_t len, jsmntok_t *tokens,
+ const size_t num_tokens) {
+ jsmntok_t *token;
+ int start;
+
+ start = parser->pos;
+
+ for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) {
+ switch (js[parser->pos]) {
+#ifndef JSMN_STRICT
+ /* In strict mode primitive must be followed by "," or "}" or "]" */
+ case ':':
+#endif
+ case '\t':
+ case '\r':
+ case '\n':
+ case ' ':
+ case ',':
+ case ']':
+ case '}':
+ goto found;
+ default:
+ /* to quiet a warning from gcc*/
+ break;
+ }
+ if (js[parser->pos] < 32 || js[parser->pos] >= 127) {
+ parser->pos = start;
+ return JSMN_ERROR_INVAL;
+ }
+ }
+#ifdef JSMN_STRICT
+ /* In strict mode primitive must be followed by a comma/object/array */
+ parser->pos = start;
+ return JSMN_ERROR_PART;
+#endif
+
+found:
+ if (tokens == NULL) {
+ parser->pos--;
+ return 0;
+ }
+ token = jsmn_alloc_token(parser, tokens, num_tokens);
+ if (token == NULL) {
+ parser->pos = start;
+ return JSMN_ERROR_NOMEM;
+ }
+ jsmn_fill_token(token, JSMN_PRIMITIVE, start, parser->pos);
+#ifdef JSMN_PARENT_LINKS
+ token->parent = parser->toksuper;
+#endif
+ parser->pos--;
+ return 0;
+}
+
+/**
+ * Fills next token with JSON string.
+ */
+static int jsmn_parse_string(jsmn_parser *parser, const char *js,
+ const size_t len, jsmntok_t *tokens,
+ const size_t num_tokens) {
+ jsmntok_t *token;
+
+ int start = parser->pos;
+
+ /* Skip starting quote */
+ parser->pos++;
+
+ for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) {
+ char c = js[parser->pos];
+
+ /* Quote: end of string */
+ if (c == '\"') {
+ if (tokens == NULL) {
+ return 0;
+ }
+ token = jsmn_alloc_token(parser, tokens, num_tokens);
+ if (token == NULL) {
+ parser->pos = start;
+ return JSMN_ERROR_NOMEM;
+ }
+ jsmn_fill_token(token, JSMN_STRING, start + 1, parser->pos);
+#ifdef JSMN_PARENT_LINKS
+ token->parent = parser->toksuper;
+#endif
+ return 0;
+ }
+
+ /* Backslash: Quoted symbol expected */
+ if (c == '\\' && parser->pos + 1 < len) {
+ int i;
+ parser->pos++;
+ switch (js[parser->pos]) {
+ /* Allowed escaped symbols */
+ case '\"':
+ case '/':
+ case '\\':
+ case 'b':
+ case 'f':
+ case 'r':
+ case 'n':
+ case 't':
+ break;
+ /* Allows escaped symbol \uXXXX */
+ case 'u':
+ parser->pos++;
+ for (i = 0; i < 4 && parser->pos < len && js[parser->pos] != '\0';
+ i++) {
+ /* If it isn't a hex character we have an error */
+ if (!((js[parser->pos] >= 48 && js[parser->pos] <= 57) || /* 0-9 */
+ (js[parser->pos] >= 65 && js[parser->pos] <= 70) || /* A-F */
+ (js[parser->pos] >= 97 && js[parser->pos] <= 102))) { /* a-f */
+ parser->pos = start;
+ return JSMN_ERROR_INVAL;
+ }
+ parser->pos++;
+ }
+ parser->pos--;
+ break;
+ /* Unexpected symbol */
+ default:
+ parser->pos = start;
+ return JSMN_ERROR_INVAL;
+ }
+ }
+ }
+ parser->pos = start;
+ return JSMN_ERROR_PART;
+}
+
+/**
+ * Parse JSON string and fill tokens.
+ */
+JSMN_API int jsmn_parse(jsmn_parser *parser, const char *js, const size_t len,
+ jsmntok_t *tokens, const unsigned int num_tokens) {
+ int r;
+ int i;
+ jsmntok_t *token;
+ int count = parser->toknext;
+
+ for (; parser->pos < len && js[parser->pos] != '\0'; parser->pos++) {
+ char c;
+ jsmntype_t type;
+
+ c = js[parser->pos];
+ switch (c) {
+ case '{':
+ case '[':
+ count++;
+ if (tokens == NULL) {
+ break;
+ }
+ token = jsmn_alloc_token(parser, tokens, num_tokens);
+ if (token == NULL) {
+ return JSMN_ERROR_NOMEM;
+ }
+ if (parser->toksuper != -1) {
+ jsmntok_t *t = &tokens[parser->toksuper];
+#ifdef JSMN_STRICT
+ /* In strict mode an object or array can't become a key */
+ if (t->type == JSMN_OBJECT) {
+ return JSMN_ERROR_INVAL;
+ }
+#endif
+ t->size++;
+#ifdef JSMN_PARENT_LINKS
+ token->parent = parser->toksuper;
+#endif
+ }
+ token->type = (c == '{' ? JSMN_OBJECT : JSMN_ARRAY);
+ token->start = parser->pos;
+ parser->toksuper = parser->toknext - 1;
+ break;
+ case '}':
+ case ']':
+ if (tokens == NULL) {
+ break;
+ }
+ type = (c == '}' ? JSMN_OBJECT : JSMN_ARRAY);
+#ifdef JSMN_PARENT_LINKS
+ if (parser->toknext < 1) {
+ return JSMN_ERROR_INVAL;
+ }
+ token = &tokens[parser->toknext - 1];
+ for (;;) {
+ if (token->start != -1 && token->end == -1) {
+ if (token->type != type) {
+ return JSMN_ERROR_INVAL;
+ }
+ token->end = parser->pos + 1;
+ parser->toksuper = token->parent;
+ break;
+ }
+ if (token->parent == -1) {
+ if (token->type != type || parser->toksuper == -1) {
+ return JSMN_ERROR_INVAL;
+ }
+ break;
+ }
+ token = &tokens[token->parent];
+ }
+#else
+ for (i = parser->toknext - 1; i >= 0; i--) {
+ token = &tokens[i];
+ if (token->start != -1 && token->end == -1) {
+ if (token->type != type) {
+ return JSMN_ERROR_INVAL;
+ }
+ parser->toksuper = -1;
+ token->end = parser->pos + 1;
+ break;
+ }
+ }
+ /* Error if unmatched closing bracket */
+ if (i == -1) {
+ return JSMN_ERROR_INVAL;
+ }
+ for (; i >= 0; i--) {
+ token = &tokens[i];
+ if (token->start != -1 && token->end == -1) {
+ parser->toksuper = i;
+ break;
+ }
+ }
+#endif
+ break;
+ case '\"':
+ r = jsmn_parse_string(parser, js, len, tokens, num_tokens);
+ if (r < 0) {
+ return r;
+ }
+ count++;
+ if (parser->toksuper != -1 && tokens != NULL) {
+ tokens[parser->toksuper].size++;
+ }
+ break;
+ case '\t':
+ case '\r':
+ case '\n':
+ case ' ':
+ break;
+ case ':':
+ parser->toksuper = parser->toknext - 1;
+ break;
+ case ',':
+ if (tokens != NULL && parser->toksuper != -1 &&
+ tokens[parser->toksuper].type != JSMN_ARRAY &&
+ tokens[parser->toksuper].type != JSMN_OBJECT) {
+#ifdef JSMN_PARENT_LINKS
+ parser->toksuper = tokens[parser->toksuper].parent;
+#else
+ for (i = parser->toknext - 1; i >= 0; i--) {
+ if (tokens[i].type == JSMN_ARRAY || tokens[i].type == JSMN_OBJECT) {
+ if (tokens[i].start != -1 && tokens[i].end == -1) {
+ parser->toksuper = i;
+ break;
+ }
+ }
+ }
+#endif
+ }
+ break;
+#ifdef JSMN_STRICT
+ /* In strict mode primitives are: numbers and booleans */
+ case '-':
+ case '0':
+ case '1':
+ case '2':
+ case '3':
+ case '4':
+ case '5':
+ case '6':
+ case '7':
+ case '8':
+ case '9':
+ case 't':
+ case 'f':
+ case 'n':
+ /* And they must not be keys of the object */
+ if (tokens != NULL && parser->toksuper != -1) {
+ const jsmntok_t *t = &tokens[parser->toksuper];
+ if (t->type == JSMN_OBJECT ||
+ (t->type == JSMN_STRING && t->size != 0)) {
+ return JSMN_ERROR_INVAL;
+ }
+ }
+#else
+ /* In non-strict mode every unquoted value is a primitive */
+ default:
+#endif
+ r = jsmn_parse_primitive(parser, js, len, tokens, num_tokens);
+ if (r < 0) {
+ return r;
+ }
+ count++;
+ if (parser->toksuper != -1 && tokens != NULL) {
+ tokens[parser->toksuper].size++;
+ }
+ break;
+
+#ifdef JSMN_STRICT
+ /* Unexpected char in strict mode */
+ default:
+ return JSMN_ERROR_INVAL;
+#endif
+ }
+ }
+
+ if (tokens != NULL) {
+ for (i = parser->toknext - 1; i >= 0; i--) {
+ /* Unmatched opened object or array */
+ if (tokens[i].start != -1 && tokens[i].end == -1) {
+ return JSMN_ERROR_PART;
+ }
+ }
+ }
+
+ return count;
+}
+
+/**
+ * Creates a new parser based over a given buffer with an array of tokens
+ * available.
+ */
+JSMN_API void jsmn_init(jsmn_parser *parser) {
+ parser->pos = 0;
+ parser->toknext = 0;
+ parser->toksuper = -1;
+}
+
+#endif /* JSMN_HEADER */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* JSMN_H */
diff --git a/json.c b/json.c
@@ -0,0 +1,137 @@
+#include <stdio.h>
+#include <string.h>
+#include "json.h"
+#include "jsmn.h"
+
+static int tok_streq(const char *js, jsmntok_t *t, const char *s) {
+ return (t->type == JSMN_STRING &&
+ (int)strlen(s) == t->end - t->start &&
+ strncmp(js + t->start, s, t->end - t->start) == 0);
+}
+
+static void scan(const char *js, jsmntok_t *t, int *i, int ntok) {
+ if (*i >= ntok) return;
+
+ if (t[*i].type == JSMN_OBJECT) {
+ int n = t[*i].size;
+ (*i)++;
+
+ const char *id = NULL, *from = NULL, *subject = NULL, *date = NULL, *body = NULL;
+ int id_len=0, from_len=0, subject_len=0, date_len=0, body_len=0;
+
+ for (int k = 0; k < n; k++) {
+ jsmntok_t *key = &t[*i]; (*i)++;
+ jsmntok_t *val = &t[*i];
+
+ /* id */
+ if (tok_streq(js, key, "id")) {
+ id = js + val->start;
+ id_len = val->end - val->start;
+ (*i)++;
+ }
+ /* headers */
+ else if (tok_streq(js, key, "headers") && val->type == JSMN_OBJECT) {
+ int hn = val->size;
+ (*i)++;
+ for (int h = 0; h < hn; h++) {
+ jsmntok_t *hkey = &t[*i]; (*i)++;
+ jsmntok_t *hval = &t[*i];
+
+ if (tok_streq(js, hkey, "From")) {
+ from = js + hval->start;
+ from_len = hval->end - hval->start;
+ } else if (tok_streq(js, hkey, "Subject")) {
+ subject = js + hval->start;
+ subject_len = hval->end - hval->start;
+ } else if (tok_streq(js, hkey, "Date")) {
+ date = js + hval->start;
+ date_len = hval->end - hval->start;
+ }
+ (*i)++;
+ }
+ }
+ /* body */
+ else if (tok_streq(js, key, "body") && val->type == JSMN_ARRAY) {
+ int bn = val->size;
+ (*i)++;
+ for (int b = 0; b < bn; b++) {
+ if (t[*i].type == JSMN_OBJECT) {
+ int on = t[*i].size;
+ (*i)++;
+ const char *ctype = NULL;
+ int ctype_len = 0;
+
+ for (int x = 0; x < on; x++) {
+ jsmntok_t *bkey = &t[*i]; (*i)++;
+ jsmntok_t *bval = &t[*i];
+
+ if (tok_streq(js, bkey, "content-type")) {
+ ctype = js + bval->start;
+ ctype_len = bval->end - bval->start;
+ } else if (tok_streq(js, bkey, "content")) {
+ if (ctype && strncmp(ctype, "text/plain", ctype_len) == 0) {
+ body = js + bval->start;
+ body_len = bval->end - bval->start;
+ }
+ }
+ (*i)++;
+ }
+ } else {
+ (*i)++;
+ }
+ }
+ }
+ else {
+ /* skip value */
+ if (val->type == JSMN_OBJECT || val->type == JSMN_ARRAY) {
+ int skip = val->size * 2;
+ (*i)++;
+ for (int s = 0; s < skip; s++) (*i)++;
+ } else {
+ (*i)++;
+ }
+ }
+ }
+
+ /* If this object looks like a message, print it */
+ if (id && subject && from && date) {
+ printf("Message-ID: %.*s\n", id_len, id);
+ printf("From: %.*s\n", from_len, from);
+ printf("Subject: %.*s\n", subject_len, subject);
+ printf("Date: %.*s\n", date_len, date);
+ if (body) {
+ printf("Body:\n%.*s\n", body_len, body);
+ }
+ printf("--------------------------------------------------\n");
+ }
+ return;
+ }
+
+ /* recurse arrays */
+ if (t[*i].type == JSMN_ARRAY) {
+ int n = t[*i].size;
+ (*i)++;
+ for (int k = 0; k < n; k++) {
+ scan(js, t, i, ntok);
+ }
+ return;
+ }
+
+ (*i)++;
+}
+
+void parse_mail_json(const char *json, int len) {
+ jsmn_parser p;
+ jsmn_init(&p);
+
+ jsmntok_t tokens[4096];
+ int ntok = jsmn_parse(&p, json, len, tokens, 4096);
+ if (ntok < 0) {
+ fprintf(stderr, "json: parse error\n");
+ return;
+ }
+
+ int i = 0;
+ scan(json, tokens, &i, ntok);
+}
+
diff --git a/json.h b/json.h
@@ -0,0 +1,8 @@
+#ifndef JSON_H
+#define JSON_H
+
+/* Parse JSON buffer and print extracted mail fields */
+void parse_mail_json(const char *json, int len);
+
+#endif
+
diff --git a/stamail.c b/stamail.c
@@ -0,0 +1,30 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include "json.h"
+
+int main(void) {
+ /* Slurp stdin */
+ char *buf = NULL;
+ size_t cap = 0, len = 0;
+ int c;
+
+ while ((c = getchar()) != EOF) {
+ if (len + 1 >= cap) {
+ cap = cap ? cap * 2 : 4096;
+ buf = realloc(buf, cap);
+ if (!buf) {
+ perror("realloc");
+ return 1;
+ }
+ }
+ buf[len++] = c;
+ }
+
+ if (!buf) return 0;
+
+ parse_mail_json(buf, len);
+
+ free(buf);
+ return 0;
+}
+
