Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fixes #23668; migrates from pcre to pcre2 #24405

Open
wants to merge 8 commits into
base: devel
Choose a base branch
from
+758 −177
Open

fixes #23668; migrates from pcre to pcre2 #24405

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8c2ec2a
fixes #23668; migrates from pcre to pcre2
ringabout Nov 4, 2024
817af7e
fixes libpcre2-8.0.dylib on macosx
ringabout Nov 4, 2024
ce1761d
progress
ringabout Nov 5, 2024
cbf6846
Merge branch 'pr_pcre_re' of https://github.com/nim-lang/Nim into pr_…
ringabout Nov 5, 2024
cb802af
try libpcre2-8-0.dll
ringabout Nov 5, 2024
27fc4fe
clean up
ringabout Nov 5, 2024
0e3ac70
progress
ringabout Nov 5, 2024
07de39c
progress
ringabout Nov 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion lib/impure/nre.nim
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
#
# Nim's Runtime Library
# (c) Copyright 2015 Nim Contributors
# (c) Copyright 2024 Nim Contributors
#
# See the file "copying.txt", included in this
# distribution, for details about the copyright.
Expand Down
16 changes: 6 additions & 10 deletions lib/impure/re.nim
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#
#
# Nim's Runtime Library
# (c) Copyright 2012 Andreas Rumpf
# (c) Copyright 2024 Andreas Rumpf
#
# See the file "copying.txt", included in this
# distribution, for details about the copyright.
Expand Down Expand Up @@ -114,15 +114,11 @@ proc re*(s: string, flags = {reStudy}): Regex =
if reIgnoreCase in flags:
options = options or CASELESS
result.h = rawCompile(s, cast[csize_t](ZERO_TERMINATED), options)
# if reStudy in flags:
# var msg: cstring = ""
# var options: cint = 0
# var hasJit: cint = 0
# if pcre2.config(pcre2.CONFIG_JIT, addr hasJit) == 0:
# if hasJit == 1'i32:
# options = pcre.STUDY_JIT_COMPILE
# result.e = pcre.study(result.h, options, addr msg)
# if not isNil(msg): raiseInvalidRegex($msg)
if reStudy in flags: # TODO: add reJit
var hasJit: cint = 0
if pcre2.config(pcre2.CONFIG_JIT, addr hasJit) == 0:
if hasJit == 1'i32 and jit_compile(result.h, pcre2.JIT_COMPLETE) != 0:
raiseInvalidRegex("JIT compilation failed.")

proc rex*(s: string, flags = {reStudy, reExtended}): Regex =
## Constructor for extended regular expressions.
Expand Down
150 changes: 22 additions & 128 deletions lib/wrappers/pcre2.nim
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,58 +1,19 @@
#
#
# Nim's Runtime Library
# (c) Copyright 2015 Andreas Rumpf
# (c) Copyright 2024 Nim Contributors
#
# See the file "copying.txt", included in this
# distribution, for details about the copyright.
#

# The current PCRE version information.
# The current PCRE2 version information.

const
PCRE_MAJOR* = 8
PCRE_MINOR* = 36
PCRE_PRERELEASE* = true
PCRE_DATE* = "2014-09-26"

# When an application links to a PCRE DLL in Windows, the symbols that are
# imported have to be identified as such. When building PCRE, the appropriate
# export setting is defined in pcre_internal.h, which includes this file. So we
# don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL.

# By default, we use the standard "extern" declarations.

# Allow for C++ users

# Public options. Some are compile-time only, some are run-time only, and some
# are both. Most of the compile-time options are saved with the compiled regex
# so that they can be inspected during studying (and therefore JIT compiling).
# Note that pcre_study() has its own set of options. Originally, all the options
# defined here used distinct bits. However, almost all the bits in a 32-bit word
# are now used, so in order to conserve them, option bits that were previously
# only recognized at matching time (i.e. by pcre_exec() or pcre_dfa_exec()) may
# also be used for compile-time options that affect only compiling and are not
# relevant for studying or JIT compiling.
#
# Some options for pcre_compile() change its behaviour but do not affect the
# behaviour of the execution functions. Other options are passed through to the
# execution functions and affect their behaviour, with or without affecting the
# behaviour of pcre_compile().
#
# Options that can be passed to pcre_compile() are tagged Cx below, with these
# variants:
#
# C1 Affects compile only
# C2 Does not affect compile; affects exec, dfa_exec
# C3 Affects compile, exec, dfa_exec
# C4 Affects compile, exec, dfa_exec, study
# C5 Affects compile, exec, study
#
# Options that can be set for pcre_exec() and/or pcre_dfa_exec() are flagged
# with E and D, respectively. They take precedence over C3, C4, and C5 settings
# passed from pcre_compile(). Those that are compatible with JIT execution are
# flagged with J.

PCRE2_MAJOR* = 10
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

shouldn't this be the version of the dynamically loaded pcre2 library? the version on the OS might be anything, including much older ones?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How to load a C define from a dynamic library?

#define PCRE2_MAJOR           @PCRE2_MAJOR@
#define PCRE2_MINOR           @PCRE2_MINOR@
#define PCRE2_PRERELEASE      @PCRE2_PRERELEASE@
#define PCRE2_DATE            @PCRE2_DATE@

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

libraries usually have a function for that, to load it dynamically - even if you compile on one system, another system you run the compiled binary will have a different version making these defines entirely meaningless at best

PCRE2_MINOR* = 45
PCRE2_PRERELEASE* = true
PCRE2_DATE* = "2024-06-09"

const
ANCHORED* = 0x80000000'u32
Expand Down Expand Up @@ -540,48 +501,27 @@ proc compile*(pattern: cstring,
offset: ptr csize_t,
tableptr: pointer): ptr Pcre

proc compile2*(pattern: cstring,
options: cint,
errorcodeptr: ptr cint,
errptr: ptr cstring,
erroffset: ptr cint,
tableptr: pointer): ptr Pcre

proc config*(what: cint,
proc config*(what: uint32,
where: pointer): cint

proc copy_named_substring*(code: ptr Pcre,
subject: cstring,
ovector: ptr cint,
stringcount: cint,
stringname: cstring,
buffer: cstring,
buffersize: cint): cint

proc copy_substring*(subject: cstring,
ovector: ptr cint,
stringcount: cint,
stringnumber: cint,
buffer: cstring,
buffersize: cint): cint

proc dfa_match*(code: ptr Pcre,
subject: cstring,
length: cint,
startoffset: cint,
options: cint,
ovector: ptr cint,
ovecsize: cint,
length: csize_t,
startoffset: csize_t,
options: uint32,
ovector: ptr MatchData,
ovecsize: pointer, # TODO: pcre2_match_context
workspace: ptr cint,
wscount: cint): cint
wscount: csize_t): cint

proc match*(code: ptr Pcre,
subject: cstring,
length: csize_t,
startoffset: csize_t,
options: uint32,
ovector: ptr MatchData,
ovecsize: pointer): cint
ovecsize: pointer # TODO: pcre2_match_context
): cint

proc match_data_create*(size: uint32, ctx: ptr GeneralContext): ptr MatchData

Expand All @@ -598,68 +538,22 @@ proc get_ovector_count*(ovector: ptr MatchData): uint32

proc jit_match*(code: ptr Pcre,
subject: cstring,
length: cint,
startoffset: cint,
options: cint,
ovector: ptr cint,
ovecsize: cint,
jstack: ptr JitStack): cint

# proc free_substring*(stringptr: cstring)

# proc free_substring_list*(stringptr: cstringArray)
length: csize_t,
startoffset: csize_t,
options: uint32,
ovector: ptr MatchData,
ovecsize: pointer # TODO: pcre2_match_context
): cint

proc code_free*(code: ptr Pcre)

proc pattern_info*(code: ptr Pcre,
what: uint32,
where: pointer): cint

proc get_named_substring*(code: ptr Pcre,
subject: cstring,
ovector: ptr cint,
stringcount: cint,
stringname: cstring,
stringptr: cstringArray): cint

proc get_stringnumber*(code: ptr Pcre,
name: cstring): cint

proc get_stringtable_entries*(code: ptr Pcre,
name: cstring,
first: cstringArray,
last: cstringArray): cint

proc get_substring*(subject: cstring,
ovector: ptr cint,
stringcount: cint,
stringnumber: cint,
stringptr: cstringArray): cint

proc get_substring_list*(subject: cstring,
ovector: ptr cint,
stringcount: cint,
listptr: ptr cstringArray): cint

proc maketables*(): pointer

proc refcount*(code: ptr Pcre,
adjust: cint): cint

proc version*(): cstring

# JIT compiler related functions.

# proc jit_stack_alloc*(startsize: cint,
# maxsize: cint): ptr JitStack

# proc jit_stack_free*(stack: ptr JitStack)

# proc assign_jit_stack*(extra: ptr ExtraData,
# callback: JitCallback,
# data: pointer)

proc jit_free_unused_memory*()
proc jit_compile*(code: ptr Pcre, options: uint32): cint


{.pop.}
Expand Down