patchwork_csv_utils 0.1.7-x86_64-darwin → 0.1.9-x86_64-darwin

Sign up to get free protection for your applications and to get access to all the features.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 6716d509dcd08fa0114772079eb4ee4c910d9fcba2e239292661f7394ae20579
4
- data.tar.gz: 97b20c9b75784359b32bf352156827c62f1d63d29cb00833ce826ae9db1ba08a
3
+ metadata.gz: 2e212bd3e73eeacfee9ebfcb560843920d212939254bfff6ffef90ca3a36fe42
4
+ data.tar.gz: a22f483c32e99467a020e3ff9a64809fbf7d9946974da06f565f27dc27b46c9b
5
5
  SHA512:
6
- metadata.gz: 4cb36630ed56de19331bc54206aaed38cfe1901b68ca4b4822c16d5141d8f0a7e374fa1c508b951dbf9182bcef3ffa5f2e0c8fa116b4ed63b148f6ebbddbf076
7
- data.tar.gz: 5cc6c6c1a0edf9ef86b42fab23aaa2937b1a80fcad5518a1f15fd3fe22d0ace8d3a534bac85f46a83a25a1dadc6328d210806f616f561dc9fb5bbe712e2f5a8b
6
+ metadata.gz: 2d731b4b50a025bee35941e48a5f5bdc4f57c0a829c69daa66610f08b354370a52502f12a2c28aab85260dc05b02d74d421a48f8d661a0cc9914546f9ed01d86
7
+ data.tar.gz: b46e0f9280ee98c6f4439dff004c0e9716ae61cbae2d615e1d0b81adb4bdd3b489b460af42cf4b436c315dfd8347dfb5069bafbb43117c678343002123165a0f
data/Gemfile.lock CHANGED
@@ -1,7 +1,7 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- patchwork_csv_utils (0.1.7)
4
+ patchwork_csv_utils (0.1.9)
5
5
 
6
6
  GEM
7
7
  remote: https://rubygems.org/
@@ -67,4 +67,4 @@ DEPENDENCIES
67
67
  rubocop (~> 1.21)
68
68
 
69
69
  BUNDLED WITH
70
- 2.4.4
70
+ 2.4.10
@@ -3,9 +3,9 @@ use std::fs::File;
3
3
 
4
4
  use chrono::{NaiveDate, NaiveDateTime, NaiveTime, Utc};
5
5
  use csv::{StringRecord, Writer};
6
- use magnus::{RArray, Ruby};
6
+ use magnus::{Error, RArray, Ruby};
7
7
 
8
- use crate::utils::{FileExtension, magnus_err, missing_header};
8
+ use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error};
9
9
 
10
10
  pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusions: RArray) -> magnus::error::Result<()> {
11
11
  if !csv_path.has_extension(&["csv"]) {
@@ -19,6 +19,7 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
19
19
  let mut wtr = Writer::from_path(target_path).map_err(|e| magnus_err(ruby, e, "target_path"))?;
20
20
  let headers = csv.headers().map_err(|e| magnus_err(ruby, e, "csv_path headers"))?;
21
21
  let header_map: HashMap<String, usize> = headers.iter().enumerate().map(|(i, h)| (h.to_string(), i)).collect();
22
+ let inverse_header_map: HashMap<usize, String> = headers.iter().enumerate().map(|(i, h)| (i, h.to_string())).collect();
22
23
 
23
24
  wtr.write_byte_record(headers.as_byte_record()).map_err(|e| magnus_err(ruby, e, "write_byte_record"))?;
24
25
 
@@ -41,13 +42,13 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
41
42
  let record = record.iter().enumerate().map(|(i, c)| {
42
43
  let c = c.trim_end();
43
44
  if i == *date {
44
- let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
45
+ let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, "Date"))?;
45
46
  date_value = current;
46
47
  Ok(current.to_string())
47
48
  } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
48
- let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
49
- let datetime = transform_time_to_datetime(date_value, current_time);
50
- Ok(datetime.to_string())
49
+ if c.is_empty() { return Ok(c.to_string()); }
50
+ let column_name = get_column_name(&inverse_header_map, &i);
51
+ process_datetime(ruby, ri, date_value, c, &column_name)
51
52
  } else {
52
53
  Ok(c.to_string())
53
54
  }
@@ -62,15 +63,39 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
62
63
  Ok(())
63
64
  }
64
65
 
66
+ fn process_datetime(ruby: &Ruby, ri: usize, date_value: NaiveDateTime, c: &str, column_name: &String) -> magnus::error::Result<String> {
67
+ let maybe_correct = correct_datetime(c);
68
+ if let Some(correct) = maybe_correct {
69
+ return Ok(correct.to_string());
70
+ }
71
+
72
+ let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, column_name))?;
73
+ let datetime = transform_time_to_datetime(date_value, current_time);
74
+ Ok(datetime.to_string())
75
+ }
76
+
77
+ fn get_column_name(inverse_header_map: &HashMap<usize, String>, i: &usize) -> String {
78
+ let unknown = "Unknown".to_string();
79
+ let column_name = inverse_header_map.get(&i).unwrap_or(&unknown);
80
+ column_name.to_string()
81
+ }
82
+
65
83
  fn skip_excluded_rows(request_id: &usize, r: &StringRecord, exclusions: &Vec<String>) -> bool {
66
84
  let value = r.get(*request_id).unwrap_or_default();
67
85
  exclusions.contains(&value.to_string())
68
86
  }
69
87
 
70
88
  fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
89
+ let maybe_correct = correct_datetime(s);
90
+ if maybe_correct.is_some() { return maybe_correct; }
91
+
71
92
  NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
72
93
  }
73
94
 
95
+ fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
96
+ NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
97
+ }
98
+
74
99
  fn string_to_time(s: &str) -> Option<NaiveTime> {
75
100
  NaiveTime::parse_from_str(s, "%H:%M").ok()
76
101
  }
@@ -79,10 +104,6 @@ fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveTime) -> NaiveDateTime
79
104
  NaiveDateTime::new(t1.date(), t2)
80
105
  }
81
106
 
82
- fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: usize) -> magnus::Error {
83
- magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
84
- }
85
-
86
107
  fn has_empty_first_col_skip_row(record: &StringRecord) -> bool {
87
108
  record[0].is_empty()
88
109
  }
@@ -15,6 +15,10 @@ fn magnus_err<E: Error>(ruby: &Ruby, e: E, msg: &str) -> magnus::Error {
15
15
  magnus::Error::new(ruby.exception_standard_error(), format!("{}: {}", msg, e.to_string()))
16
16
  }
17
17
 
18
+ fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
19
+ magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
20
+ }
21
+
18
22
  pub trait FileExtension {
19
23
  fn has_extension<S: AsRef<str>>(&self, extensions: &[S]) -> bool;
20
24
  }
@@ -6,7 +6,7 @@ use calamine::{Data, open_workbook, Range, Reader, Xls};
6
6
  use chrono::{NaiveDateTime, Utc};
7
7
  use magnus::{RArray, Ruby};
8
8
 
9
- use crate::utils::{FileExtension, magnus_err, missing_header};
9
+ use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error};
10
10
 
11
11
  pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String, exclusions: RArray) -> magnus::error::Result<()> {
12
12
  if !xls_path.has_extension(&["xls"]) {
@@ -44,6 +44,9 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
44
44
  if skip_excluded_rows(&request_id, r, &exclusions) { continue; }
45
45
  if skip_empty_rows(r) { continue; }
46
46
  if skip_rows_with_no_request_id(&request_id, r) { continue; }
47
+ if date_value_is_not_present(&date, r) {
48
+ return Err(magnus::Error::new(ruby.exception_standard_error(), format!("Date value is not present in row: {}", ri)));
49
+ }
47
50
 
48
51
  for (i, c) in r.iter().enumerate() {
49
52
  match *c {
@@ -53,7 +56,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
53
56
  }
54
57
  Data::Float(ref f) => write!(dest, "{}", f),
55
58
  Data::DateTime(ref d) => {
56
- let mut current = d.as_datetime().unwrap_or_default();
59
+ let mut current = d.as_datetime().ok_or(to_datetime_error(ruby, &d.to_string(), ri, "Date"))?;
57
60
  if i == *date {
58
61
  date_value = current;
59
62
  } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
@@ -74,6 +77,10 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
74
77
  Ok(())
75
78
  }
76
79
 
80
+ fn date_value_is_not_present(date: &usize, r: &[Data]) -> bool {
81
+ r[*date] == Data::Empty
82
+ }
83
+
77
84
  fn skip_excluded_rows(request_id: &usize, r: &[Data], exclusions: &Vec<String>) -> bool {
78
85
  let value = r[*request_id].to_string();
79
86
  exclusions.contains(&value.to_string())
Binary file
Binary file
Binary file
Binary file
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module CsvUtils
4
- VERSION = '0.1.7'
4
+ VERSION = '0.1.9'
5
5
  end
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: 0.1.7
4
+ version: 0.1.9
5
5
  platform: x86_64-darwin
6
6
  authors:
7
7
  - kingsley.hendrickse
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2024-08-07 00:00:00.000000000 Z
11
+ date: 2024-08-08 00:00:00.000000000 Z
12
12
  dependencies: []
13
13
  description: Deduplication of CSV files and XLS to CSV conversion.
14
14
  email: