[nginx] PCRE2 and PCRE binary compatibility.

[Mathew Heard]

By the way have you seen sregex ? Given its built with many of the
same principles as nginx and PREG(1/2) compatible maybe it might be of
interest?

And Merry Christmas for those who celebrate.

On Sat, 25 Dec 2021 at 09:11, Maxim Dounin <mdounin at mdounin.ru> wrote:
>
> details:   https://hg.nginx.org/nginx/rev/fbbb5ce52995
> branches:
> changeset: 7982:fbbb5ce52995
> user:      Maxim Dounin <mdounin at mdounin.ru>
> date:      Sat Dec 25 01:07:16 2021 +0300
> description:
> PCRE2 and PCRE binary compatibility.
>
> With this change, dynamic modules using nginx regex interface can be used
> regardless of the variant of the PCRE library nginx was compiled with.
>
> If a module is compiled with different PCRE library variant, in case of
> ngx_regex_exec() errors it will report wrong function name in error
> messages.  This is believed to be tolerable, given that fixing this will
> require interface changes.
>
> diffstat:
>
>  src/core/ngx_regex.c |  46 ++++++++++++++++++++++++++++++++++++++++++----
>  src/core/ngx_regex.h |  17 ++++++-----------
>  2 files changed, 48 insertions(+), 15 deletions(-)
>
> diffs (139 lines):
>
> diff -r 0b5f12d5c531 -r fbbb5ce52995 src/core/ngx_regex.c
> --- a/src/core/ngx_regex.c      Sat Dec 25 01:07:15 2021 +0300
> +++ b/src/core/ngx_regex.c      Sat Dec 25 01:07:16 2021 +0300
> @@ -118,6 +118,7 @@ ngx_regex_compile(ngx_regex_compile_t *r
>      char                   *p;
>      u_char                  errstr[128];
>      size_t                  erroff;
> +    uint32_t                options;
>      pcre2_code             *re;
>      ngx_regex_elt_t        *elt;
>      pcre2_general_context  *gctx;
> @@ -152,11 +153,24 @@ ngx_regex_compile(ngx_regex_compile_t *r
>          ngx_regex_malloc_done();
>      }
>
> +    options = 0;
> +
> +    if (rc->options & NGX_REGEX_CASELESS) {
> +        options |= PCRE2_CASELESS;
> +    }
> +
> +    if (rc->options & ~NGX_REGEX_CASELESS) {
> +        rc->err.len = ngx_snprintf(rc->err.data, rc->err.len,
> +                            "regex \"%V\" compilation failed: invalid options",
> +                            &rc->pattern)
> +                      - rc->err.data;
> +        return NGX_ERROR;
> +    }
> +
>      ngx_regex_malloc_init(rc->pool);
>
> -    re = pcre2_compile(rc->pattern.data, rc->pattern.len,
> -                       (uint32_t) rc->options, &errcode, &erroff,
> -                       ngx_regex_compile_context);
> +    re = pcre2_compile(rc->pattern.data, rc->pattern.len, options,
> +                       &errcode, &erroff, ngx_regex_compile_context);
>
>      /* ensure that there is no current pool */
>      ngx_regex_malloc_done();
> @@ -252,11 +266,26 @@ ngx_regex_compile(ngx_regex_compile_t *r
>      char             *p;
>      pcre             *re;
>      const char       *errstr;
> +    ngx_uint_t        options;
>      ngx_regex_elt_t  *elt;
>
> +    options = 0;
> +
> +    if (rc->options & NGX_REGEX_CASELESS) {
> +        options |= PCRE_CASELESS;
> +    }
> +
> +    if (rc->options & ~NGX_REGEX_CASELESS) {
> +        rc->err.len = ngx_snprintf(rc->err.data, rc->err.len,
> +                            "regex \"%V\" compilation failed: invalid options",
> +                            &rc->pattern)
> +                      - rc->err.data;
> +        return NGX_ERROR;
> +    }
> +
>      ngx_regex_malloc_init(rc->pool);
>
> -    re = pcre_compile((const char *) rc->pattern.data, (int) rc->options,
> +    re = pcre_compile((const char *) rc->pattern.data, (int) options,
>                        &errstr, &erroff, NULL);
>
>      /* ensure that there is no current pool */
> @@ -413,6 +442,15 @@ failed:
>      return rc;
>  }
>
> +#else
> +
> +ngx_int_t
> +ngx_regex_exec(ngx_regex_t *re, ngx_str_t *s, int *captures, ngx_uint_t size)
> +{
> +    return pcre_exec(re->code, re->extra, (const char *) s->data, s->len,
> +                     0, 0, captures, size);
> +}
> +
>  #endif
>
>
> diff -r 0b5f12d5c531 -r fbbb5ce52995 src/core/ngx_regex.h
> --- a/src/core/ngx_regex.h      Sat Dec 25 01:07:15 2021 +0300
> +++ b/src/core/ngx_regex.h      Sat Dec 25 01:07:16 2021 +0300
> @@ -19,7 +19,6 @@
>  #include <pcre2.h>
>
>  #define NGX_REGEX_NO_MATCHED   PCRE2_ERROR_NOMATCH   /* -1 */
> -#define NGX_REGEX_CASELESS     PCRE2_CASELESS
>
>  typedef pcre2_code  ngx_regex_t;
>
> @@ -28,7 +27,6 @@ typedef pcre2_code  ngx_regex_t;
>  #include <pcre.h>
>
>  #define NGX_REGEX_NO_MATCHED   PCRE_ERROR_NOMATCH    /* -1 */
> -#define NGX_REGEX_CASELESS     PCRE_CASELESS
>
>  typedef struct {
>      pcre        *code;
> @@ -38,10 +36,13 @@ typedef struct {
>  #endif
>
>
> +#define NGX_REGEX_CASELESS     0x00000001
> +
> +
>  typedef struct {
>      ngx_str_t     pattern;
>      ngx_pool_t   *pool;
> -    ngx_int_t     options;
> +    ngx_uint_t    options;
>
>      ngx_regex_t  *regex;
>      int           captures;
> @@ -61,19 +62,13 @@ typedef struct {
>  void ngx_regex_init(void);
>  ngx_int_t ngx_regex_compile(ngx_regex_compile_t *rc);
>
> -#if (NGX_PCRE2)
> -
>  ngx_int_t ngx_regex_exec(ngx_regex_t *re, ngx_str_t *s, int *captures,
>      ngx_uint_t size);
> +
> +#if (NGX_PCRE2)
>  #define ngx_regex_exec_n       "pcre2_match()"
> -
>  #else
> -
> -#define ngx_regex_exec(re, s, captures, size)                                \
> -    pcre_exec(re->code, re->extra, (const char *) (s)->data, (s)->len, 0, 0, \
> -              captures, size)
>  #define ngx_regex_exec_n       "pcre_exec()"
> -
>  #endif
>
>  ngx_int_t ngx_regex_exec_array(ngx_array_t *a, ngx_str_t *s, ngx_log_t *log);
> _______________________________________________
> nginx-devel mailing list
> nginx-devel at nginx.org
> http://mailman.nginx.org/mailman/listinfo/nginx-devel