patchwork_csv_utils 0.1.13-x86_64-linux → 0.1.15-x86_64-linux

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a786c19115a7385e97f6eb02a4b59d60c39eb28e92dcee390ed268ba28b44c4e
-  data.tar.gz: 871457cba4388fdb138aa450e201f14aa387279e8181889d9e1bdf37b6c4140a
+  metadata.gz: e996387ff4380d6fd613b82146c030db354bba2a6b922b1726c1bbbb41863554
+  data.tar.gz: 88feb5ae5c6847311576c69cc6f9f6dcdd4fedda10acc0adc2303239a59dab9e
 SHA512:
-  metadata.gz: 535c10c53645b0220289e1c0f98e170fa108c4d841c33023486a5acde941f0237e8c002f25e0211dceb1cb08edfdf73e13cb7dd6fda27721a2b5d85c24bd7ea1
-  data.tar.gz: d03168eef93bb5a6bf6e16e75ca2a80f148f04538776f1828aec54750c677c97a32eac682ecfc9238c74d217c34b5e5060d03fd924483277fafa7b5896df4f94
+  metadata.gz: 558188ef57034619feae637bf5e561660635d656a2724441cc82b53075afef6b5de18035999359d9496ccb354f756048e8d7028936586ed85c0e966efe55ab88
+  data.tar.gz: 60ce7b849799296e6c9afc57c5fcbafa8753b33c2949c5fccd77a1f32c8d39f56eff817ac2fe438299531eef859e33ecaf9c051731778373e11e0c57de0d9a7d

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.13)
+    patchwork_csv_utils (0.1.15)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -14,8 +14,8 @@ gem install patchwork_csv_utils
 ```irb
 require 'csv_utils'
 CsvUtils.dedup('file1.csv', 'file2.csv', 'output.csv', ['mandatory_headers'])
-CsvUtils.to_csv('file1.xls', 'output_file1.csv', ['request_ids_to_skip'], ['mandatory_headers'])
-CsvUtils.transform_csv('file1.xls', 'output_file1.csv', ['request_ids_to_skip'], ['mandatory_headers'])
+CsvUtils.to_csv('file1.xls', 'output_file1.csv', ['request_ids_to_skip'], ['mandatory_headers'], ['status_exclusions'])
+CsvUtils.transform_csv('file1.xls', 'output_file1.csv', ['request_ids_to_skip'], ['mandatory_headers'], ['status_exclusions'])
 ```
 
 ## Release

data/ext/csv_utils/src/lib.rs

@@ -9,7 +9,7 @@ pub mod utils;
 fn init() -> Result<(), magnus::Error> {
     let module = define_module("CsvUtils")?;
     module.define_singleton_method("dedup", function!(dedup, 4))?;
-    module.define_singleton_method("to_csv", function!(to_csv, 4))?;
-    module.define_singleton_method("transform_csv", function!(transform_csv, 4))?;
+    module.define_singleton_method("to_csv", function!(to_csv, 5))?;
+    module.define_singleton_method("transform_csv", function!(transform_csv, 5))?;
     Ok(())
 }

data/ext/csv_utils/src/utils/csv.rs

@@ -1,6 +1,6 @@
 use std::collections::HashMap;
 use std::fs::File;
-
+use calamine::Data;
 use chrono::{NaiveDate, NaiveDateTime, NaiveTime, Utc};
 use csv::{Reader, StringRecord, Writer};
 use magnus::{Error, RArray, Ruby};
@@ -9,12 +9,14 @@ use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error,
 
 pub fn transform_csv(ruby: &Ruby, csv_path: String,
                      target_path: String, exclusions: RArray,
-                     mandatory_headers: RArray, ) -> magnus::error::Result<()> {
+                     mandatory_headers: RArray,
+                     status_exclusions: RArray) -> magnus::error::Result<()> {
     if !csv_path.has_extension(&["csv"]) {
         return Err(Error::new(ruby.exception_standard_error(), "csv_path must be a csv file".to_string()));
     }
 
     let exclusions = RArray::to_vec(exclusions)?;
+    let status_exclusions = RArray::to_vec(status_exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
 
     let csv_file = File::open(csv_path).map_err(|e| magnus_err(ruby, e, "csv_path"))?;
@@ -38,12 +40,14 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String,
     let end = header_map.get("End").ok_or(missing_header(ruby, "End"))?;
     let actual_start = header_map.get("Actual Start").ok_or(missing_header(ruby, "Actual Start"))?;
     let actual_end = header_map.get("Actual End").ok_or(missing_header(ruby, "Actual End"))?;
+    let status = header_map.get("Status");
 
     let mandatory_records = get_mandatory_records(&ruby, &mut csv, &headers_list, &mandatory_headers)?;
 
     for (ri, record) in mandatory_records.iter().enumerate() {
 
         if skip_excluded_rows(request_id, &record, &exclusions) { continue; }
+        if skip_excluded_status_rows(&status, &record, &status_exclusions) { continue; }
         if has_empty_row_skip(&record) { continue; }
         if has_empty_first_col_skip_row(&record) { continue; }
 
@@ -124,6 +128,12 @@ fn skip_excluded_rows(request_id: &usize, r: &StringRecord, exclusions: &Vec<Str
     exclusions.contains(&value.to_string())
 }
 
+fn skip_excluded_status_rows(status: &Option<&usize>, r: &StringRecord, exclusions: &Vec<String>) -> bool {
+    status
+        .map(|index| exclusions.contains(&r[*index].to_string()))
+        .unwrap_or(false)
+}
+
 fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
     let maybe_correct = correct_datetime(s);
     if maybe_correct.is_some() { return maybe_correct; }

data/ext/csv_utils/src/utils/xls.rs

@@ -11,7 +11,8 @@ use crate::utils::{FileExtension, magnus_err, missing_header, to_datetime_error,
 pub fn to_csv(ruby: &Ruby, xls_path: String,
               target_path: String,
               exclusions: RArray,
-              mandatory_headers: RArray
+              mandatory_headers: RArray,
+              status_exclusions: RArray,
 ) -> magnus::error::Result<()> {
     if !xls_path.has_extension(&["xls"]) {
         return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls file".to_string()));
@@ -19,6 +20,7 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
 
     let exclusions = RArray::to_vec(exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
+    let status_exclusions = RArray::to_vec(status_exclusions)?;
 
     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()))?;
     let range = workbook.worksheet_range_at(0)
@@ -26,7 +28,7 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
         .and_then(|r| r.map_err(|e| magnus_err(ruby, e, "could not read worksheet range")))?;
 
     let headers = range.headers().ok_or(magnus::Error::new(ruby.exception_standard_error(), "no headers found in xls".to_string()))?;
-    let headers_list : Vec<String> = headers.iter().map(|h| h.to_string()).collect();
+    let headers_list: Vec<String> = headers.iter().map(|h| h.to_string()).collect();
 
     if let Some(value) =
         check_mandatory_headers(ruby, &headers_list, &mandatory_headers, "csv") { return value; }
@@ -35,13 +37,14 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
     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()))?;
     let mut dest = BufWriter::new(csv_out_file);
 
-    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list)
+    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions)
 }
 
 fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
                        header_map: HashMap<String, usize>, exclusions: Vec<String>,
                        mandatory_headers: Vec<String>,
-                       headers_list: Vec<String>) -> magnus::error::Result<()> {
+                       headers_list: Vec<String>,
+                       status_exclusions: Vec<String>) -> magnus::error::Result<()> {
     let n = mandatory_headers.len() - 1;
     let request_id = header_map.get("Request Id").ok_or(missing_header(ruby, "Request Id"))?;
     let date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
@@ -49,6 +52,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
     let end = header_map.get("End").ok_or(missing_header(ruby, "End"))?;
     let actual_start = header_map.get("Actual Start").ok_or(missing_header(ruby, "Actual Start"))?;
     let actual_end = header_map.get("Actual End").ok_or(missing_header(ruby, "Actual End"))?;
+    let status = header_map.get("Status");
 
     let mandatory_rows = get_mandatory_records(ruby, range, &headers_list, &mandatory_headers)?;
 
@@ -56,6 +60,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
         let mut date_value = Utc::now().naive_utc();
 
         if skip_excluded_rows(&request_id, &r, &exclusions) { continue; }
+        if skip_excluded_status_rows(&status, &r, &status_exclusions) { continue; }
         if skip_empty_rows(&r) { continue; }
         if skip_rows_with_no_request_id(&request_id, &r) { continue; }
         if date_value_is_not_present(&date, &r) {
@@ -63,7 +68,6 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
         }
 
         for (i, c) in mandatory_headers.iter().enumerate() {
-
             let column_index = header_map.get(c).ok_or(missing_header(ruby, c))?;
             let c = r.get(*column_index).ok_or(missing_value(ruby, c))?;
 
@@ -125,6 +129,12 @@ fn skip_excluded_rows(request_id: &usize, r: &Vec<&Data>, exclusions: &Vec<Strin
     exclusions.contains(&value.to_string())
 }
 
+fn skip_excluded_status_rows(status: &Option<&usize>, r: &Vec<&Data>, exclusions: &Vec<String>) -> bool {
+    status
+        .map(|index| exclusions.contains(&r[*index].to_string()))
+        .unwrap_or(false)
+}
+
 fn skip_empty_rows(r: &Vec<&Data>) -> bool {
     r.into_iter().all(|c| c == &&Data::Empty)
 }
@@ -149,7 +159,6 @@ fn clean_strings(s: &str) -> String {
     s.replace("\n", " ")
         .replace("\r", " ")
         .replace("\"", "")
-        .replace("'", "")
 }
 
 struct XlsMandatoryColumn<'a> {

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.13'
+  VERSION = '0.1.15'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.13
+  version: 0.1.15
 platform: x86_64-linux
 authors:
 - kingsley.hendrickse
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-09-04 00:00:00.000000000 Z
+date: 2024-10-31 00:00:00.000000000 Z
 dependencies: []
 description: Deduplication of CSV files and XLS to CSV conversion.
 email: