simple_text_extract 3.0.0 → 3.0.1
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/CHANGELOG.md +5 -1
- data/Gemfile.lock +1 -1
- data/lib/simple_text_extract/extract.rb +6 -3
- data/lib/simple_text_extract/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 4d97ba86e11c6ad6e14e3e2af600eddc00378747a693a51be38a15da7c73b9b5
|
|
4
|
+
data.tar.gz: 401dd3aee14d95cc750397bc7b9e6393dbb49eb45d9369d39096a5a6046cb0d8
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 76156def8c686dca8dba70e7ac36fb58a65757610c7cdb9bfd73c9a13c161d64db1730a21bcf5746a75398cfea2bc1a47e52acfd2e038c414e1a102df05b7854
|
|
7
|
+
data.tar.gz: f327f06da4692531b051e291f20529889e123c508f15643ade8486819b2ac91ab04bde79b1ed5b6091d3bf8e28c3895fcdbf3cf1148367c16fb2743190aab159
|
data/CHANGELOG.md
CHANGED
|
@@ -1,4 +1,8 @@
|
|
|
1
|
-
##
|
|
1
|
+
## 3.0.1 (2023-04-17)
|
|
2
|
+
|
|
3
|
+
- Fixes printing of Roo::Excelx::Cell::Empty for empty rows
|
|
4
|
+
|
|
5
|
+
## 3.0.0 (2023-04-14)
|
|
2
6
|
|
|
3
7
|
- [BREAKING CHANGE] Improves format of text extracts to better support post processing into sentences/rows. This will only cause issues if you have tests/code that relies on the specific format of whitespace characters in the resulting extracts. For example, the docx extract will now preserve newline characters.
|
|
4
8
|
- Improves memory allocation for xlsx files using `Roo#each_row_streaming`
|
data/Gemfile.lock
CHANGED
|
@@ -88,10 +88,13 @@ class SimpleTextExtract::Extract
|
|
|
88
88
|
|
|
89
89
|
text = []
|
|
90
90
|
|
|
91
|
-
spreadsheet.sheets.
|
|
92
|
-
text <<
|
|
91
|
+
spreadsheet.sheets.each_with_index do |name, i|
|
|
92
|
+
text << "# Sheet Index: #{i}"
|
|
93
|
+
text << "# Sheet Name: #{name}"
|
|
93
94
|
|
|
94
|
-
spreadsheet.sheet(name)&.each_row_streaming
|
|
95
|
+
spreadsheet.sheet(name)&.each_row_streaming do |row|
|
|
96
|
+
text << row.filter(&:present?).join(" ")
|
|
97
|
+
end
|
|
95
98
|
end
|
|
96
99
|
|
|
97
100
|
text.join("\n")
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: simple_text_extract
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 3.0.
|
|
4
|
+
version: 3.0.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Nick Weiland
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-04-
|
|
11
|
+
date: 2023-04-17 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: roo
|