patchwork_csv_utils 0.1.3-x86_64-linux → 0.1.5-x86_64-linux
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 +28 -11
- data/lib/csv_utils/2.7/csv_utils.so +0 -0
- data/lib/csv_utils/3.0/csv_utils.so +0 -0
- data/lib/csv_utils/3.1/csv_utils.so +0 -0
- data/lib/csv_utils/3.2/csv_utils.so +0 -0
- data/lib/csv_utils/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 7db641e3c590f814c0a9b89a555da4b4b333cfccdcc11759a9cd1a7faa9f6638
|
4
|
+
data.tar.gz: 2ba2941e6384563b6a44fafb715940ead548aadbc319466ed316911f7ca18148
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 2856df18a42dc6019c3a6b6d02aa9d88ccd6384ac46a157bc762c4848dd601bd1a31dd072831bd8dafe301ab8514c930bbff159f7f22a47aeb8ff0aafbd932ee
|
7
|
+
data.tar.gz: 926f5673c06e7419f63ff66094e2c35d7aae36df5b8eb09f3604ea4ee77add83b36bf8087f36ffe495e00b728a5052277738f11da3037260484aeb2232086be7
|
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, 2))?;
|
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
|
|
@@ -8,13 +8,15 @@ use magnus::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
|
11
|
+
pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String) -> magnus::error::Result<()> {
|
12
12
|
if !xls_path.has_extension(&["xls"]) {
|
13
13
|
return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls file".to_string()));
|
14
14
|
}
|
15
15
|
|
16
16
|
let mut workbook: Xls<_> = open_workbook(xls_path.clone()).map_err(|e| magnus_err(ruby, e, format!("could not open xls: {}", xls_path).as_str()))?;
|
17
|
-
let range = workbook.
|
17
|
+
let range = workbook.worksheet_range_at(0)
|
18
|
+
.ok_or(magnus::Error::new(ruby.exception_standard_error(), "no worksheet found in xls".to_string()))
|
19
|
+
.and_then(|r| r.map_err(|e| magnus_err(ruby, e, "could not read worksheet range")))?;
|
18
20
|
|
19
21
|
let headers = range.headers().ok_or(magnus::Error::new(ruby.exception_standard_error(), "no headers found in xls".to_string()))?;
|
20
22
|
let header_map: HashMap<String, usize> = headers.iter().enumerate().map(|(i, h)| (h.to_string(), i)).collect();
|
@@ -29,17 +31,16 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
|
|
29
31
|
for (ri, r) in range.rows().enumerate() {
|
30
32
|
let mut date_value = Utc::now().naive_utc();
|
31
33
|
|
32
|
-
if r
|
33
|
-
|
34
|
-
}
|
34
|
+
if skip_empty_rows(r) { continue; }
|
35
|
+
if skip_rows_with_no_request_id(&header_map, r) { continue; }
|
35
36
|
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
let actual_end = header_map.get("Actual End").ok_or(missing_header(ruby, "Actual End"))?;
|
37
|
+
let date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
|
38
|
+
let start = header_map.get("Start").ok_or(missing_header(ruby, "Start"))?;
|
39
|
+
let end = header_map.get("End").ok_or(missing_header(ruby, "End"))?;
|
40
|
+
let actual_start = header_map.get("Actual Start").ok_or(missing_header(ruby, "Actual Start"))?;
|
41
|
+
let actual_end = header_map.get("Actual End").ok_or(missing_header(ruby, "Actual End"))?;
|
42
42
|
|
43
|
+
for (i, c) in r.iter().enumerate() {
|
43
44
|
match *c {
|
44
45
|
Data::Empty => Ok(()),
|
45
46
|
Data::String(ref s) | Data::DateTimeIso(ref s) | Data::DurationIso(ref s) => {
|
@@ -68,6 +69,22 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
|
|
68
69
|
Ok(())
|
69
70
|
}
|
70
71
|
|
72
|
+
fn skip_empty_rows(r: &[Data]) -> bool {
|
73
|
+
if r.iter().all(|c| c == &Data::Empty) {
|
74
|
+
return true;
|
75
|
+
}
|
76
|
+
false
|
77
|
+
}
|
78
|
+
|
79
|
+
fn skip_rows_with_no_request_id(header_map: &HashMap<String, usize>, r: &[Data]) -> bool {
|
80
|
+
if let Some(request_id) = header_map.get("Request Id") {
|
81
|
+
if r[*request_id] == Data::Empty {
|
82
|
+
return true;
|
83
|
+
}
|
84
|
+
}
|
85
|
+
false
|
86
|
+
}
|
87
|
+
|
71
88
|
fn missing_header(ruby: &Ruby, header: &str) -> magnus::Error {
|
72
89
|
magnus::Error::new(ruby.exception_standard_error(), format!("Missing '{}' header in xls", header))
|
73
90
|
}
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
data/lib/csv_utils/version.rb
CHANGED