patchwork_csv_utils 0.1.4-arm64-darwin → 0.1.6-arm64-darwin
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/Gemfile.lock +1 -1
- data/ext/csv_utils/src/lib.rs +1 -1
- data/ext/csv_utils/src/utils/dedup.rs +22 -0
- data/ext/csv_utils/src/utils/xls.rs +21 -4
- data/lib/csv_utils/2.7/csv_utils.bundle +0 -0
- data/lib/csv_utils/3.0/csv_utils.bundle +0 -0
- data/lib/csv_utils/3.1/csv_utils.bundle +0 -0
- data/lib/csv_utils/3.2/csv_utils.bundle +0 -0
- data/lib/csv_utils/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: 29f014ebb0d7fe82e824325e564767deb1cfed92e24c1f487171457214316ac2
|
4
|
+
data.tar.gz: 608a2edb81ccedebc584762b5c30a2eb24e2c002fae1d28190cf7cf307cc23b3
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: de08a499be3bd3106978ba9b56b81afd3b1bfb634262405aefae74cab36543390d9f825e2bcdf2d25601bbdcea2fec3f4853bff470a39a89a484846477b2dd59
|
7
|
+
data.tar.gz: 6b25c5917e837b3de71570f0d12c14d92cf3ef588d36ca660611fbae4a6ca17cc2c04af641304f7dc755cb69ea57b5a38c324ca09b9322af62dd8d0900659718
|
data/Gemfile.lock
CHANGED
data/ext/csv_utils/src/lib.rs
CHANGED
@@ -8,6 +8,6 @@ pub mod utils;
|
|
8
8
|
fn init() -> Result<(), magnus::Error> {
|
9
9
|
let module = define_module("CsvUtils")?;
|
10
10
|
module.define_singleton_method("dedup", function!(dedup, 3))?;
|
11
|
-
module.define_singleton_method("to_csv", function!(to_csv,
|
11
|
+
module.define_singleton_method("to_csv", function!(to_csv, 3))?;
|
12
12
|
Ok(())
|
13
13
|
}
|
@@ -33,12 +33,20 @@ pub fn dedup(ruby: &Ruby, previous_csv_path: String, new_csv_path: String, targe
|
|
33
33
|
let mut previous_records = vec![];
|
34
34
|
for previous_record in previous_csv.records() {
|
35
35
|
let previous_record = previous_record.map_err(|e| magnus_err(ruby, e, "previous_record"))?;
|
36
|
+
|
37
|
+
if has_empty_row_skip(&previous_record) { continue; }
|
38
|
+
if has_empty_first_col_skip_row(&previous_record) { continue; }
|
39
|
+
|
36
40
|
let previous_record = previous_record.into_iter().map(|r| r.trim_end()).collect::<StringRecord>();
|
37
41
|
previous_records.push(previous_record)
|
38
42
|
}
|
39
43
|
|
40
44
|
for new_record in new_csv.records() {
|
41
45
|
let new_record = new_record.map_err(|e| magnus_err(ruby, e, "new_record"))?;
|
46
|
+
|
47
|
+
if has_empty_row_skip(&new_record) { continue; }
|
48
|
+
if has_empty_first_col_skip_row(&new_record) { continue; }
|
49
|
+
|
42
50
|
let new_record = new_record.into_iter().map(|r| r.trim_end()).collect::<StringRecord>();
|
43
51
|
if !previous_records.contains(&new_record) {
|
44
52
|
wtr.write_byte_record(new_record.as_byte_record()).unwrap();
|
@@ -50,4 +58,18 @@ pub fn dedup(ruby: &Ruby, previous_csv_path: String, new_csv_path: String, targe
|
|
50
58
|
Ok(())
|
51
59
|
}
|
52
60
|
|
61
|
+
fn has_empty_first_col_skip_row(previous_record: &StringRecord) -> bool {
|
62
|
+
if previous_record[0].is_empty() {
|
63
|
+
return true;
|
64
|
+
}
|
65
|
+
false
|
66
|
+
}
|
67
|
+
|
68
|
+
fn has_empty_row_skip(record: &StringRecord) -> bool {
|
69
|
+
if record.iter().all(|r| r.is_empty()) {
|
70
|
+
return true;
|
71
|
+
}
|
72
|
+
false
|
73
|
+
}
|
74
|
+
|
53
75
|
|
@@ -4,11 +4,17 @@ use std::io::{BufWriter, Write};
|
|
4
4
|
|
5
5
|
use calamine::{Data, open_workbook, Range, Reader, Xls};
|
6
6
|
use chrono::{NaiveDateTime, Utc};
|
7
|
-
use magnus::Ruby;
|
7
|
+
use magnus::{RArray, Ruby};
|
8
8
|
|
9
9
|
use crate::utils::{FileExtension, magnus_err};
|
10
10
|
|
11
|
-
pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String) -> magnus::error::Result<()> {
|
11
|
+
pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String, exclusions: RArray) -> magnus::error::Result<()> {
|
12
|
+
let exclusions = RArray::to_vec(exclusions)?;
|
13
|
+
|
14
|
+
println!("xls_path: {:?}", xls_path);
|
15
|
+
println!("target_path: {:?}", target_path);
|
16
|
+
println!("exclusions: {:?}", exclusions);
|
17
|
+
|
12
18
|
if !xls_path.has_extension(&["xls"]) {
|
13
19
|
return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls file".to_string()));
|
14
20
|
}
|
@@ -23,14 +29,15 @@ pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String) -> magnus::err
|
|
23
29
|
let csv_out_file = File::create(target_path.clone()).map_err(|e| magnus_err(ruby, e, format!("could not create csv file: {}", target_path).as_str()))?;
|
24
30
|
let mut dest = BufWriter::new(csv_out_file);
|
25
31
|
|
26
|
-
write_csv(ruby, &mut dest, &range, header_map)
|
32
|
+
write_csv(ruby, &mut dest, &range, header_map, exclusions)
|
27
33
|
}
|
28
34
|
|
29
|
-
fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_map: HashMap<String, usize>) -> magnus::error::Result<()> {
|
35
|
+
fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_map: HashMap<String, usize>, exclusions: Vec<String>) -> magnus::error::Result<()> {
|
30
36
|
let n = range.get_size().1 - 1;
|
31
37
|
for (ri, r) in range.rows().enumerate() {
|
32
38
|
let mut date_value = Utc::now().naive_utc();
|
33
39
|
|
40
|
+
if skip_excluded_rows(&header_map, r, &exclusions) { continue; }
|
34
41
|
if skip_empty_rows(r) { continue; }
|
35
42
|
if skip_rows_with_no_request_id(&header_map, r) { continue; }
|
36
43
|
|
@@ -69,6 +76,16 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
|
|
69
76
|
Ok(())
|
70
77
|
}
|
71
78
|
|
79
|
+
fn skip_excluded_rows(header_map: &HashMap<String, usize>, r: &[Data], exclusions: &Vec<String>) -> bool {
|
80
|
+
if let Some(request_id) = header_map.get("Request Id") {
|
81
|
+
let value = r[*request_id].to_string();
|
82
|
+
if exclusions.contains(&value) {
|
83
|
+
return true;
|
84
|
+
}
|
85
|
+
}
|
86
|
+
false
|
87
|
+
}
|
88
|
+
|
72
89
|
fn skip_empty_rows(r: &[Data]) -> bool {
|
73
90
|
if r.iter().all(|c| c == &Data::Empty) {
|
74
91
|
return true;
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/lib/csv_utils/version.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: patchwork_csv_utils
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.6
|
5
5
|
platform: arm64-darwin
|
6
6
|
authors:
|
7
7
|
- kingsley.hendrickse
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-08-
|
11
|
+
date: 2024-08-06 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: Deduplication of CSV files and XLS to CSV conversion.
|
14
14
|
email:
|