parsekit 0.1.3 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/ext/parsekit/Cargo.toml +4 -4
- data/lib/parsekit/version.rb +1 -1
- data/lib/parsekit.rb +8 -2
- metadata +3 -6
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: b32f09ec6af6545f7db84b9c6c6f10a27998d95b2305ec5f5a5bef4a80a2a717
|
|
4
|
+
data.tar.gz: 7b36ef18a14bd708ae885c5b101f822cf6cb088c1ba729b0398bd4d5522ab0fb
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2f5b479a90c550ea25c4a0a6f19afbb10aee5a51b14f7a27868857249605e6b72e045288eb2019805c8281d499d31b8d0597c96bea3c1cee87753430541116a1
|
|
7
|
+
data.tar.gz: a1ab174853194a4806e1c88606912005bc074b072893681c17e3e271339baadd401e7849ebc026305809507c7ca0b6d30584941c4a94f5619d339000df3e06dd
|
data/ext/parsekit/Cargo.toml
CHANGED
|
@@ -14,13 +14,13 @@ name = "parsekit"
|
|
|
14
14
|
magnus = { version = "0.8", features = ["rb-sys"] }
|
|
15
15
|
# Document parsing - testing embedded C libraries
|
|
16
16
|
# MuPDF builds from source and statically links
|
|
17
|
-
mupdf = { version = "0.
|
|
17
|
+
mupdf = { version = "0.7", default-features = false, features = [] }
|
|
18
18
|
# OCR - Using tesseract-rs for both system and bundled modes
|
|
19
|
-
tesseract-rs = "0.
|
|
19
|
+
tesseract-rs = "0.2" # Tesseract with optional bundling
|
|
20
20
|
image = "0.25" # Image processing library (match rusty-tesseract's version)
|
|
21
|
-
calamine = "0.
|
|
21
|
+
calamine = "0.35" # Excel parsing
|
|
22
22
|
docx-rs = "0.4" # Word document parsing
|
|
23
|
-
quick-xml = "0.
|
|
23
|
+
quick-xml = "0.40" # XML parsing
|
|
24
24
|
zip = "8.2" # ZIP archive handling for PPTX
|
|
25
25
|
serde_json = "1.0" # JSON parsing
|
|
26
26
|
regex = "1.10" # Text parsing
|
data/lib/parsekit/version.rb
CHANGED
data/lib/parsekit.rb
CHANGED
|
@@ -2,9 +2,15 @@
|
|
|
2
2
|
|
|
3
3
|
require_relative "parsekit/version"
|
|
4
4
|
|
|
5
|
-
# Load the
|
|
5
|
+
# Load the compiled Rust extension. Precompiled (platform) gems install it into a
|
|
6
|
+
# Ruby-ABI-versioned subdir (lib/parsekit/<major.minor>/parsekit.{so,bundle}) so a
|
|
7
|
+
# single fat gem can carry a binary per Ruby version; source/dev builds place it flat
|
|
8
|
+
# at lib/parsekit/parsekit.{so,bundle}. Try the versioned path first, fall back to the
|
|
9
|
+
# flat one. Resolution goes through $LOAD_PATH (`require`, never `require_relative`)
|
|
10
|
+
# because RubyGems installs native extensions outside the gem's lib/ dir.
|
|
6
11
|
begin
|
|
7
|
-
|
|
12
|
+
RUBY_VERSION =~ /(\d+\.\d+)/
|
|
13
|
+
require "parsekit/#{Regexp.last_match(1)}/parsekit"
|
|
8
14
|
rescue LoadError
|
|
9
15
|
require "parsekit/parsekit"
|
|
10
16
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,13 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: parsekit
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Chris Petersen
|
|
8
|
-
autorequire:
|
|
9
8
|
bindir: exe
|
|
10
9
|
cert_chain: []
|
|
11
|
-
date:
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
12
11
|
dependencies:
|
|
13
12
|
- !ruby/object:Gem::Dependency
|
|
14
13
|
name: rb_sys
|
|
@@ -110,7 +109,6 @@ metadata:
|
|
|
110
109
|
homepage_uri: https://github.com/scientist-labs/parsekit
|
|
111
110
|
source_code_uri: https://github.com/scientist-labs/parsekit
|
|
112
111
|
changelog_uri: https://github.com/scientist-labs/parsekit/blob/main/CHANGELOG.md
|
|
113
|
-
post_install_message:
|
|
114
112
|
rdoc_options: []
|
|
115
113
|
require_paths:
|
|
116
114
|
- lib
|
|
@@ -125,8 +123,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
125
123
|
- !ruby/object:Gem::Version
|
|
126
124
|
version: '0'
|
|
127
125
|
requirements: []
|
|
128
|
-
rubygems_version: 3.
|
|
129
|
-
signing_key:
|
|
126
|
+
rubygems_version: 3.6.9
|
|
130
127
|
specification_version: 4
|
|
131
128
|
summary: Ruby document parsing toolkit with PDF and OCR support
|
|
132
129
|
test_files: []
|