diff options
| author | kumquat-ir <66188216+kumquat-ir@users.noreply.github.com> | 2021-04-17 09:46:11 -0700 |
|---|---|---|
| committer | kumquat-ir <66188216+kumquat-ir@users.noreply.github.com> | 2021-04-17 09:46:11 -0700 |
| commit | e668aa0f95f4f56a1ac4320f014662d279c22708 (patch) | |
| tree | 7462597a5b709081b15c224d928b36018c74248f /libraries/tomlc99 | |
| parent | 13afad80fb9b17503621dc63509113203af8887c (diff) | |
| download | PrismLauncher-e668aa0f95f4f56a1ac4320f014662d279c22708.tar.gz PrismLauncher-e668aa0f95f4f56a1ac4320f014662d279c22708.tar.bz2 PrismLauncher-e668aa0f95f4f56a1ac4320f014662d279c22708.zip | |
switch to new toml library
Diffstat (limited to 'libraries/tomlc99')
| -rw-r--r-- | libraries/tomlc99/CMakeLists.txt | 10 | ||||
| -rw-r--r-- | libraries/tomlc99/LICENSE | 22 | ||||
| -rw-r--r-- | libraries/tomlc99/README.md | 194 | ||||
| -rw-r--r-- | libraries/tomlc99/include/toml.h | 175 | ||||
| -rw-r--r-- | libraries/tomlc99/src/toml.c | 2300 |
5 files changed, 2701 insertions, 0 deletions
diff --git a/libraries/tomlc99/CMakeLists.txt b/libraries/tomlc99/CMakeLists.txt new file mode 100644 index 00000000..60786923 --- /dev/null +++ b/libraries/tomlc99/CMakeLists.txt @@ -0,0 +1,10 @@ +project(tomlc99) + +set(tomlc99_SOURCES +include/toml.h +src/toml.c +) + +add_library(tomlc99 STATIC ${tomlc99_SOURCES}) + +target_include_directories(tomlc99 PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include) diff --git a/libraries/tomlc99/LICENSE b/libraries/tomlc99/LICENSE new file mode 100644 index 00000000..a3292b16 --- /dev/null +++ b/libraries/tomlc99/LICENSE @@ -0,0 +1,22 @@ +MIT License + +Copyright (c) 2017 CK Tan +https://github.com/cktan/tomlc99 + +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. diff --git a/libraries/tomlc99/README.md b/libraries/tomlc99/README.md new file mode 100644 index 00000000..6715b5be --- /dev/null +++ b/libraries/tomlc99/README.md @@ -0,0 +1,194 @@ +# tomlc99 + +TOML in c99; v1.0 compliant. + +If you are looking for a C++ library, you might try this wrapper: [https://github.com/cktan/tomlcpp](https://github.com/cktan/tomlcpp). + +* Compatible with [TOML v1.0.0](https://toml.io/en/v1.0.0). +* Tested with multiple test suites, including +[BurntSushi/toml-test](https://github.com/BurntSushi/toml-test) and +[iarna/toml-spec-tests](https://github.com/iarna/toml-spec-tests). +* Provides very simple and intuitive interface. + + +## Usage + +Please see the `toml.h` file for details. What follows is a simple example that +parses this config file: + +```toml +[server] + host = "www.example.com" + port = [ 8080, 8181, 8282 ] +``` + +The steps for getting values from our file is usually : + +1. Parse the TOML file. +2. Traverse and locate a table in TOML. +3. Extract values from the table. +4. Free up allocated memory. + +Below is an example of parsing the values from the example table. + +```c +#include <stdio.h> +#include <string.h> +#include <errno.h> +#include <stdlib.h> +#include "toml.h" + +static void error(const char* msg, const char* msg1) +{ + fprintf(stderr, "ERROR: %s%s\n", msg, msg1?msg1:""); + exit(1); +} + + +int main() +{ + FILE* fp; + char errbuf[200]; + + // 1. Read and parse toml file + fp = fopen("sample.toml", "r"); + if (!fp) { + error("cannot open sample.toml - ", strerror(errno)); + } + + toml_table_t* conf = toml_parse_file(fp, errbuf, sizeof(errbuf)); + fclose(fp); + + if (!conf) { + error("cannot parse - ", errbuf); + } + + // 2. Traverse to a table. + toml_table_t* server = toml_table_in(conf, "server"); + if (!server) { + error("missing [server]", ""); + } + + // 3. Extract values + toml_datum_t host = toml_string_in(server, "host"); + if (!host.ok) { + error("cannot read server.host", ""); + } + + toml_array_t* portarray = toml_array_in(server, "port"); + if (!portarray) { + error("cannot read server.port", ""); + } + + printf("host: %s\n", host.u.s); + printf("port: "); + for (int i = 0; ; i++) { + toml_datum_t port = toml_int_at(portarray, i); + if (!port.ok) break; + printf("%d ", (int)port.u.i); + } + printf("\n"); + + // 4. Free memory + free(host.u.s); + toml_free(conf); + return 0; +} +``` + +#### Accessing Table Content + +TOML tables are dictionaries where lookups are done using string keys. In +general, all access functions on tables are named `toml_*_in(...)`. + +In the normal case, you know the key and its content type, and retrievals can be done +using one of these functions: +```c +toml_string_in(tab, key); +toml_bool_in(tab, key); +toml_int_in(tab, key); +toml_double_in(tab, key); +toml_timestamp_in(tab, key); +toml_table_in(tab, key); +toml_array_in(tab, key); +``` + +You can also interrogate the keys in a table using an integer index: +```c +toml_table_t* tab = toml_parse_file(...); +for (int i = 0; ; i++) { + const char* key = toml_key_in(tab, i); + if (!key) break; + printf("key %d: %s\n", i, key); +} +``` + +#### Accessing Array Content + +TOML arrays can be deref-ed using integer indices. In general, all access methods on arrays are named `toml_*_at()`. + +To obtain the size of an array: +```c +int size = toml_array_nelem(arr); +``` + +To obtain the content of an array, use a valid index and call one of these functions: +```c +toml_string_at(arr, idx); +toml_bool_at(arr, idx); +toml_int_at(arr, idx); +toml_double_at(arr, idx); +toml_timestamp_at(arr, idx); +toml_table_at(arr, idx); +toml_array_at(arr, idx); +``` + +#### toml_datum_t + +Some `toml_*_at` and `toml_*_in` functions return a toml_datum_t +structure. The `ok` flag in the structure indicates if the function +call was successful. If so, you may proceed to read the value +corresponding to the type of the content. + +For example: +``` +toml_datum_t host = toml_string_in(tab, "host"); +if (host.ok) { + printf("host: %s\n", host.u.s); + free(host.u.s); /* FREE applies to string and timestamp types only */ +} +``` + +** IMPORTANT: if the accessed value is a string or a timestamp, you must call `free(datum.u.s)` or `free(datum.u.ts)` respectively after usage. ** + +## Building and installing + +A normal *make* suffices. You can also simply include the +`toml.c` and `toml.h` files in your project. + +Invoking `make install` will install the header and library files into +/usr/local/{include,lib}. + +Alternatively, specify `make install prefix=/a/file/path` to install into +/a/file/path/{include,lib}. + +## Testing + +To test against the standard test set provided by BurntSushi/toml-test: + +```sh +% make +% cd test1 +% bash build.sh # do this once +% bash run.sh # this will run the test suite +``` + + +To test against the standard test set provided by iarna/toml: + +```sh +% make +% cd test2 +% bash build.sh # do this once +% bash run.sh # this will run the test suite +``` diff --git a/libraries/tomlc99/include/toml.h b/libraries/tomlc99/include/toml.h new file mode 100644 index 00000000..b91ef890 --- /dev/null +++ b/libraries/tomlc99/include/toml.h @@ -0,0 +1,175 @@ +/* + MIT License + + Copyright (c) 2017 - 2019 CK Tan + https://github.com/cktan/tomlc99 + + 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 TOML_H +#define TOML_H + + +#include <stdio.h> +#include <stdint.h> + + +#ifdef __cplusplus +#define TOML_EXTERN extern "C" +#else +#define TOML_EXTERN extern +#endif + +typedef struct toml_timestamp_t toml_timestamp_t; +typedef struct toml_table_t toml_table_t; +typedef struct toml_array_t toml_array_t; +typedef struct toml_datum_t toml_datum_t; + +/* Parse a file. Return a table on success, or 0 otherwise. + * Caller must toml_free(the-return-value) after use. + */ +TOML_EXTERN toml_table_t* toml_parse_file(FILE* fp, + char* errbuf, + int errbufsz); + +/* Parse a string containing the full config. + * Return a table on success, or 0 otherwise. + * Caller must toml_free(the-return-value) after use. + */ +TOML_EXTERN toml_table_t* toml_parse(char* conf, /* NUL terminated, please. */ + char* errbuf, + int errbufsz); + +/* Free the table returned by toml_parse() or toml_parse_file(). Once + * this function is called, any handles accessed through this tab + * directly or indirectly are no longer valid. + */ +TOML_EXTERN void toml_free(toml_table_t* tab); + + +/* Timestamp types. The year, month, day, hour, minute, second, z + * fields may be NULL if they are not relevant. e.g. In a DATE + * type, the hour, minute, second and z fields will be NULLs. + */ +struct toml_timestamp_t { + struct { /* internal. do not use. */ + int year, month, day; + int hour, minute, second, millisec; + char z[10]; + } __buffer; + int *year, *month, *day; + int *hour, *minute, *second, *millisec; + char* z; +}; + + +/*----------------------------------------------------------------- + * Enhanced access methods + */ +struct toml_datum_t { + int ok; + union { + toml_timestamp_t* ts; /* ts must be freed after use */ + char* s; /* string value. s must be freed after use */ + int b; /* bool value */ + int64_t i; /* int value */ + double d; /* double value */ + } u; +}; + +/* on arrays: */ +/* ... retrieve size of array. */ +TOML_EXTERN int toml_array_nelem(const toml_array_t* arr); +/* ... retrieve values using index. */ +TOML_EXTERN toml_datum_t toml_string_at(const toml_array_t* arr, int idx); +TOML_EXTERN toml_datum_t toml_bool_at(const toml_array_t* arr, int idx); +TOML_EXTERN toml_datum_t toml_int_at(const toml_array_t* arr, int idx); +TOML_EXTERN toml_datum_t toml_double_at(const toml_array_t* arr, int idx); +TOML_EXTERN toml_datum_t toml_timestamp_at(const toml_array_t* arr, int idx); +/* ... retrieve array or table using index. */ +TOML_EXTERN toml_array_t* toml_array_at(const toml_array_t* arr, int idx); +TOML_EXTERN toml_table_t* toml_table_at(const toml_array_t* arr, int idx); + +/* on tables: */ +/* ... retrieve the key in table at keyidx. Return 0 if out of range. */ +TOML_EXTERN const char* toml_key_in(const toml_table_t* tab, int keyidx); +/* ... retrieve values using key. */ +TOML_EXTERN toml_datum_t toml_string_in(const toml_table_t* arr, const char* key); +TOML_EXTERN toml_datum_t toml_bool_in(const toml_table_t* arr, const char* key); +TOML_EXTERN toml_datum_t toml_int_in(const toml_table_t* arr, const char* key); +TOML_EXTERN toml_datum_t toml_double_in(const toml_table_t* arr, const char* key); +TOML_EXTERN toml_datum_t toml_timestamp_in(const toml_table_t* arr, const char* key); +/* .. retrieve array or table using key. */ +TOML_EXTERN toml_array_t* toml_array_in(const toml_table_t* tab, + const char* key); +TOML_EXTERN toml_table_t* toml_table_in(const toml_table_t* tab, + const char* key); + +/*----------------------------------------------------------------- + * lesser used + */ +/* Return the array kind: 't'able, 'a'rray, 'v'alue, 'm'ixed */ +TOML_EXTERN char toml_array_kind(const toml_array_t* arr); + +/* For array kind 'v'alue, return the type of values + i:int, d:double, b:bool, s:string, t:time, D:date, T:timestamp, 'm'ixed + 0 if unknown +*/ +TOML_EXTERN char toml_array_type(const toml_array_t* arr); + +/* Return the key of an array */ +TOML_EXTERN const char* toml_array_key(const toml_array_t* arr); + +/* Return the number of key-values in a table */ +TOML_EXTERN int toml_table_nkval(const toml_table_t* tab); + +/* Return the number of arrays in a table */ +TOML_EXTERN int toml_table_narr(const toml_table_t* tab); + +/* Return the number of sub-tables in a table */ +TOML_EXTERN int toml_table_ntab(const toml_table_t* tab); + +/* Return the key of a table*/ +TOML_EXTERN const char* toml_table_key(const toml_table_t* tab); + +/*-------------------------------------------------------------- + * misc + */ +TOML_EXTERN int toml_utf8_to_ucs(const char* orig, int len, int64_t* ret); +TOML_EXTERN int toml_ucs_to_utf8(int64_t code, char buf[6]); +TOML_EXTERN void toml_set_memutil(void* (*xxmalloc)(size_t), + void (*xxfree)(void*)); + + +/*-------------------------------------------------------------- + * deprecated + */ +/* A raw value, must be processed by toml_rto* before using. */ +typedef const char* toml_raw_t; +TOML_EXTERN toml_raw_t toml_raw_in(const toml_table_t* tab, const char* key); +TOML_EXTERN toml_raw_t toml_raw_at(const toml_array_t* arr, int idx); +TOML_EXTERN int toml_rtos(toml_raw_t s, char** ret); +TOML_EXTERN int toml_rtob(toml_raw_t s, int* ret); +TOML_EXTERN int toml_rtoi(toml_raw_t s, int64_t* ret); +TOML_EXTERN int toml_rtod(toml_raw_t s, double* ret); +TOML_EXTERN int toml_rtod_ex(toml_raw_t s, double* ret, char* buf, int buflen); +TOML_EXTERN int toml_rtots(toml_raw_t s, toml_timestamp_t* ret); + + +#endif /* TOML_H */ diff --git a/libraries/tomlc99/src/toml.c b/libraries/tomlc99/src/toml.c new file mode 100644 index 00000000..e46e62e6 --- /dev/null +++ b/libraries/tomlc99/src/toml.c @@ -0,0 +1,2300 @@ +/* + + MIT License + + Copyright (c) 2017 - 2021 CK Tan + https://github.com/cktan/tomlc99 + + 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. + +*/ +#define _POSIX_C_SOURCE 200809L +#include <stdio.h> +#include <stdlib.h> +#include <assert.h> +#include <errno.h> +#include <stdint.h> +#include <ctype.h> +#include <string.h> +#include <stdbool.h> +#include "toml.h" + + +static void* (*ppmalloc)(size_t) = malloc; +static void (*ppfree)(void*) = free; + +void toml_set_memutil(void* (*xxmalloc)(size_t), + void (*xxfree)(void*)) +{ + if (xxmalloc) ppmalloc = xxmalloc; + if (xxfree) ppfree = xxfree; +} + + +#define MALLOC(a) ppmalloc(a) +#define FREE(a) ppfree(a) + +static void* CALLOC(size_t nmemb, size_t sz) +{ + int nb = sz * nmemb; + void* p = MALLOC(nb); + if (p) { + memset(p, 0, nb); + } + return p; +} + + +static char* STRDUP(const char* s) +{ + int len = strlen(s); + char* p = MALLOC(len+1); + if (p) { + memcpy(p, s, len); + p[len] = 0; + } + return p; +} + +static char* STRNDUP(const char* s, size_t n) +{ + size_t len = strnlen(s, n); + char* p = MALLOC(len+1); + if (p) { + memcpy(p, s, len); + p[len] = 0; + } + return p; +} + + + +/** + * Convert a char in utf8 into UCS, and store it in *ret. + * Return #bytes consumed or -1 on failure. + */ +int toml_utf8_to_ucs(const char* orig, int len, int64_t* ret) +{ + const unsigned char* buf = (const unsigned char*) orig; + unsigned i = *buf++; + int64_t v; + + /* 0x00000000 - 0x0000007F: + 0xxxxxxx + */ + if (0 == (i >> 7)) { + if (len < 1) return -1; + v = i; + return *ret = v, 1; + } + /* 0x00000080 - 0x000007FF: + 110xxxxx 10xxxxxx + */ + if (0x6 == (i >> 5)) { + if (len < 2) return -1; + v = i & 0x1f; + for (int j = 0; j < 1; j++) { + i = *buf++; + if (0x2 != (i >> 6)) return -1; + v = (v << 6) | (i & 0x3f); + } + return *ret = v, (const char*) buf - orig; + } + + /* 0x00000800 - 0x0000FFFF: + 1110xxxx 10xxxxxx 10xxxxxx + */ + if (0xE == (i >> 4)) { + if (len < 3) return -1; + v = i & 0x0F; + for (int j = 0; j < 2; j++) { + i = *buf++; + if (0x2 != (i >> 6)) return -1; + v = (v << 6) | (i & 0x3f); + } + return *ret = v, (const char*) buf - orig; + } + + /* 0x00010000 - 0x001FFFFF: + 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (0x1E == (i >> 3)) { + if (len < 4) return -1; + v = i & 0x07; + for (int j = 0; j < 3; j++) { + i = *buf++; + if (0x2 != (i >> 6)) return -1; + v = (v << 6) | (i & 0x3f); + } + return *ret = v, (const char*) buf - orig; + } + + /* 0x00200000 - 0x03FFFFFF: + 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (0x3E == (i >> 2)) { + if (len < 5) return -1; + v = i & 0x03; + for (int j = 0; j < 4; j++) { + i = *buf++; + if (0x2 != (i >> 6)) return -1; + v = (v << 6) | (i & 0x3f); + } + return *ret = v, (const char*) buf - orig; + } + + /* 0x04000000 - 0x7FFFFFFF: + 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (0x7e == (i >> 1)) { + if (len < 6) return -1; + v = i & 0x01; + for (int j = 0; j < 5; j++) { + i = *buf++; + if (0x2 != (i >> 6)) return -1; + v = (v << 6) | (i & 0x3f); + } + return *ret = v, (const char*) buf - orig; + } + return -1; +} + + +/** + * Convert a UCS char to utf8 code, and return it in buf. + * Return #bytes used in buf to encode the char, or + * -1 on error. + */ +int toml_ucs_to_utf8(int64_t code, char buf[6]) +{ + /* http://stackoverflow.com/questions/6240055/manually-converting-unicode-codepoints-into-utf-8-and-utf-16 */ + /* The UCS code values 0xd800–0xdfff (UTF-16 surrogates) as well + * as 0xfffe and 0xffff (UCS noncharacters) should not appear in + * conforming UTF-8 streams. + */ + if (0xd800 <= code && code <= 0xdfff) return -1; + if (0xfffe <= code && code <= 0xffff) return -1; + + /* 0x00000000 - 0x0000007F: + 0xxxxxxx + */ + if (code < 0) return -1; + if (code <= 0x7F) { + buf[0] = (unsigned char) code; + return 1; + } + + /* 0x00000080 - 0x000007FF: + 110xxxxx 10xxxxxx + */ + if (code <= 0x000007FF) { + buf[0] = 0xc0 | (code >> 6); + buf[1] = 0x80 | (code & 0x3f); + return 2; + } + + /* 0x00000800 - 0x0000FFFF: + 1110xxxx 10xxxxxx 10xxxxxx + */ + if (code <= 0x0000FFFF) { + buf[0] = 0xe0 | (code >> 12); + buf[1] = 0x80 | ((code >> 6) & 0x3f); + buf[2] = 0x80 | (code & 0x3f); + return 3; + } + + /* 0x00010000 - 0x001FFFFF: + 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (code <= 0x001FFFFF) { + buf[0] = 0xf0 | (code >> 18); + buf[1] = 0x80 | ((code >> 12) & 0x3f); + buf[2] = 0x80 | ((code >> 6) & 0x3f); + buf[3] = 0x80 | (code & 0x3f); + return 4; + } + + /* 0x00200000 - 0x03FFFFFF: + 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (code <= 0x03FFFFFF) { + buf[0] = 0xf8 | (code >> 24); + buf[1] = 0x80 | ((code >> 18) & 0x3f); + buf[2] = 0x80 | ((code >> 12) & 0x3f); + buf[3] = 0x80 | ((code >> 6) & 0x3f); + buf[4] = 0x80 | (code & 0x3f); + return 5; + } + + /* 0x04000000 - 0x7FFFFFFF: + 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx + */ + if (code <= 0x7FFFFFFF) { + buf[0] = 0xfc | (code >> 30); + buf[1] = 0x80 | ((code >> 24) & 0x3f); + buf[2] = 0x80 | ((code >> 18) & 0x3f); + buf[3] = 0x80 | ((code >> 12) & 0x3f); + buf[4] = 0x80 | ((code >> 6) & 0x3f); + buf[5] = 0x80 | (code & 0x3f); + return 6; + } + + return -1; +} + +/* + * TOML has 3 data structures: value, array, table. + * Each of them can have identification key. + */ +typedef struct toml_keyval_t toml_keyval_t; +struct toml_keyval_t { + const char* key; /* key to this value */ + const char* val; /* the raw value */ +}; + +typedef struct toml_arritem_t toml_arritem_t; +struct toml_arritem_t { + int valtype; /* for value kind: 'i'nt, 'd'ouble, 'b'ool, 's'tring, 't'ime, 'D'ate, 'T'imestamp */ + char* val; + toml_array_t* arr; + toml_table_t* tab; +}; + + +struct toml_array_t { + const char* key; /* key to this array */ + int kind; /* element kind: 'v'alue, 'a'rray, or 't'able, 'm'ixed */ + int type; /* for value kind: 'i'nt, 'd'ouble, 'b'ool, 's'tring, 't'ime, 'D'ate, 'T'imestamp, 'm'ixed */ + + int nitem; /* number of elements */ + toml_arritem_t* item; +}; + + +struct toml_table_t { + const char* key; /* key to this table */ + bool implicit; /* table was created implicitly */ + bool readonly; /* no more modification allowed */ + + /* key-values in the table */ + int nkval; + toml_keyval_t** kval; + + /* arrays in the table */ + int narr; + toml_array_t** arr; + + /* tables in the table */ + int ntab; + toml_table_t** tab; +}; + + +static inline void xfree(const void* x) { if (x) FREE((void*)(intptr_t)x); } + + +enum tokentype_t { + INVALID, + DOT, + COMMA, + EQUAL, + LBRACE, + RBRACE, + NEWLINE, + LBRACKET, + RBRACKET, + STRING, +}; +typedef enum tokentype_t tokentype_t; + +typedef struct token_t token_t; +struct token_t { + tokentype_t tok; + int lineno; + char* ptr; /* points into context->start */ + int len; + int eof; +}; + + +typedef struct context_t context_t; +struct context_t { + char* start; + char* stop; + char* errbuf; + int errbufsz; + + token_t tok; + toml_table_t* root; + toml_table_t* curtab; + + struct { + int top; + char* key[10]; + token_t tok[10]; + } tpath; + +}; + +#define STRINGIFY(x) #x +#define TOSTRING(x) STRINGIFY(x) +#define FLINE __FILE__ ":" TOSTRING(__LINE__) + +static int next_token(context_t* ctx, int dotisspecial); + +/* + Error reporting. Call when an error is detected. Always return -1. +*/ +static int e_outofmemory(context_t* ctx, const char* fline) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "ERROR: out of memory (%s)", fline); + return -1; +} + + +static int e_internal(context_t* ctx, const char* fline) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "internal error (%s)", fline); + return -1; +} + +static int e_syntax(context_t* ctx, int lineno, const char* msg) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "line %d: %s", lineno, msg); + return -1; +} + +static int e_badkey(context_t* ctx, int lineno) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "line %d: bad key", lineno); + return -1; +} + +static int e_keyexists(context_t* ctx, int lineno) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "line %d: key exists", lineno); + return -1; +} + +static int e_forbid(context_t* ctx, int lineno, const char* msg) +{ + snprintf(ctx->errbuf, ctx->errbufsz, "line %d: %s", lineno, msg); + return -1; +} + +static void* expand(void* p, int sz, int newsz) +{ + void* s = MALLOC(newsz); + if (!s) return 0; + + memcpy(s, p, sz); + FREE(p); + return s; +} + +static void** expand_ptrarr(void** p, int n) +{ + void** s = MALLOC((n+1) * sizeof(void*)); + if (!s) return 0; + + s[n] = 0; + memcpy(s, p, n * sizeof(void*)); + FREE(p); + return s; +} + +static toml_arritem_t* expand_arritem(toml_arritem_t* p, int n) +{ + toml_arritem_t* pp = expand(p, n*sizeof(*p), (n+1)*sizeof(*p)); + if (!pp) return 0; + + memset(&pp[n], 0, sizeof(pp[n])); + return pp; +} + + +static char* norm_lit_str(const char* src, int srclen, + int multiline, + char* errbuf, int errbufsz) +{ + char* dst = 0; /* will write to dst[] and return it */ + int max = 0; /* max size of dst[] */ + int off = 0; /* cur offset in dst[] */ + const char* sp = src; + const char* sq = src + srclen; + int ch; + + /* scan forward on src */ + for (;;) { + if (off >= max - 10) { /* have some slack for misc stuff */ + int newmax = max + 50; + char* x = expand(dst, max, newmax); + if (!x) { + xfree(dst); + snprintf(errbuf, errbufsz, "out of memory"); + return 0; + } + dst = x; + max = newmax; + } + + /* finished? */ + if (sp >= sq) break; + + ch = *sp++; + /* control characters other than tab is not allowed */ + if ((0 <= ch && ch <= 0x08) + || (0x0a <= ch && ch <= 0x1f) + || (ch == 0x7f)) { + if (! (multiline && (ch == '\r' || ch == '\n'))) { + xfree(dst); + snprintf(errbuf, errbufsz, "invalid char U+%04x", ch); + return 0; + } + } + + // a plain copy suffice + dst[off++] = ch; + } + + dst[off++] = 0; + return dst; +} + + + + +/* + * Convert src to raw unescaped utf-8 string. + * Returns NULL if error with errmsg in errbuf. + */ +static char* norm_basic_str(const char* src, int srclen, + int multiline, + char* errbuf, int errbufsz) +{ + char* dst = 0; /* will write to dst[] and return it */ + int max = 0; /* max size of dst[] */ + int off = 0; /* cur offset in dst[] */ + const char* sp = src; + const char* sq = src + srclen; + int ch; + + /* scan forward on src */ + for (;;) { + if (off >= max - 10) { /* have some slack for misc stuff */ + int newmax = max + 50; + char* x = expand(dst, max, newmax); + if (!x) { + xfree(dst); + snprintf(errbuf, errbufsz, "out of memory"); + return 0; + } + dst = x; + max = newmax; + } + + /* finished? */ + if (sp >= sq) break; + + ch = *sp++; + if (ch != '\\') { + /* these chars must be escaped: U+0000 to U+0008, U+000A to U+001F, U+007F */ + if ((0 <= ch && ch <= 0x08) + || (0x0a <= ch && ch <= 0x1f) + || (ch == 0x7f)) { + if (! (multiline && (ch == '\r' || ch == '\n'))) { + xfree(dst); + snprintf(errbuf, errbufsz, "invalid char U+%04x", ch); + return 0; + } + } + + // a plain copy suffice + dst[off++] = ch; + continue; + } + + /* ch was backslash. we expect the escape char. */ + if (sp >= sq) { + snprintf(errbuf, errbufsz, "last backslash is invalid"); + xfree(dst); + return 0; + } + + /* for multi-line, we want to kill line-ending-backslash ... */ + if (multiline) { + + // if there is only whitespace after the backslash ... + if (sp[strspn(sp, " \t\r")] == '\n') { + /* skip all the following whitespaces */ + sp += strspn(sp, " \t\r\n"); + continue; + } + } + + /* get the escaped char */ + ch = *sp++; + switch (ch) { + case 'u': case 'U': + { + int64_t ucs = 0; + int nhex = (ch == 'u' ? 4 : 8); + for (int i = 0; i < nhex; i++) { + if (sp >= sq) { + snprintf(errbuf, errbufsz, "\\%c expects %d hex chars", ch, nhex); + xfree(dst); + return 0; + } + ch = *sp++; + int v = ('0' <= ch && ch <= '9') + ? ch - '0' + : (('A' <= ch && ch <= 'F') ? ch - 'A' + 10 : -1); + if (-1 == v) { + snprintf(errbuf, errbufsz, "invalid hex chars for \\u or \\U"); + xfree(dst); + return 0; + } + ucs = ucs * 16 + v; + } + int n = toml_ucs_to_utf8(ucs, &dst[off]); + if (-1 == n) { + snprintf(errbuf, errbufsz, "illegal ucs code in \\u or \\U"); + xfree(dst); + return 0; + } + off += n; + } + continue; + + case 'b': ch = '\b'; break; + case 't': ch = '\t'; break; + case 'n': ch = '\n'; break; + case 'f': ch = '\f'; break; + case 'r': ch = '\r'; break; + case '"': ch = '"'; break; + case '\\': ch = '\\'; break; + default: + snprintf(errbuf, errbufsz, "illegal escape char \\%c", ch); + xfree(dst); + return 0; + } + + dst[off++] = ch; + } + + // Cap with NUL and return it. + dst[off++] = 0; + return dst; +} + + +/* Normalize a key. Convert all special chars to raw unescaped utf-8 chars. */ +static char* normalize_key(context_t* ctx, token_t strtok) +{ + const char* sp = strtok.ptr; + const char* sq = strtok.ptr + strtok.len; + int lineno = strtok.lineno; + char* ret; + int ch = *sp; + char ebuf[80]; + + /* handle quoted string */ + if (ch == '\'' || ch == '\"') { + /* if ''' or """, take 3 chars off front and back. Else, take 1 char off. */ + int multiline = 0; + if (sp[1] == ch && sp[2] == ch) { + sp += 3, sq -= 3; + multiline = 1; + } + else + sp++, sq--; + + if (ch == '\'') { + /* for single quote, take it verbatim. */ + if (! (ret = STRNDUP(sp, sq - sp))) { + e_outofmemory(ctx, FLINE); + return 0; + } + } else { + /* for double quote, we need to normalize */ + ret = norm_basic_str(sp, sq - sp, multiline, ebuf, sizeof(ebuf)); + if (!ret) { + e_syntax(ctx, lineno, ebuf); + return 0; + } + } + + /* newlines are not allowed in keys */ + if (strchr(ret, '\n')) { + xfree(ret); + e_badkey(ctx, lineno); + return 0; + } + return ret; + } + + /* for bare-key allow only this regex: [A-Za-z0-9_-]+ */ + const char* xp; + for (xp = sp; xp != sq; xp++) { + int k = *xp; + if (isalnum(k)) continue; + if (k == '_' || k == '-') continue; + e_badkey(ctx, lineno); + return 0; + } + + /* dup and return it */ + if (! (ret = STRNDUP(sp, sq - sp))) { + e_outofmemory(ctx, FLINE); + return 0; + } + return ret; +} + + +/* + * Look up key in tab. Return 0 if not found, or + * 'v'alue, 'a'rray or 't'able depending on the element. + */ +static int check_key(toml_table_t* tab, const char* key, + toml_keyval_t** ret_val, + toml_array_t** ret_arr, + toml_table_t** ret_tab) +{ + int i; + void* dummy; + + if (!ret_tab) ret_tab = (toml_table_t**) &dummy; + if (!ret_arr) ret_arr = (toml_array_t**) &dummy; + if (!ret_val) ret_val = (toml_keyval_t**) &dummy; + + *ret_tab = 0; *ret_arr = 0; *ret_val = 0; + + for (i = 0; i < tab->nkval; i++) { + if (0 == strcmp(key, tab->kval[i]->key)) { + *ret_val = tab->kval[i]; + return 'v'; + } + } + for (i = 0; i < tab->narr; i++) { + if (0 == strcmp(key, tab->arr[i]->key)) { + *ret_arr = tab->arr[i]; + return 'a'; + } + } + for (i = 0; i < tab->ntab; i++) { + if (0 == strcmp(key, tab->tab[i]->key)) { + *ret_tab = tab->tab[i]; + return 't'; + } + } + return 0; +} + + +static int key_kind(toml_table_t* tab, const char* key) +{ + return check_key(tab, key, 0, 0, 0); +} + +/* Create a keyval in the tab |
