patchwork_csv_utils 0.1.20-x86_64-darwin → 0.1.22-x86_64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cdf477614b412f9458bb7e3872f2445b8158aff33ea38ca7981f97009acd90cc
-  data.tar.gz: 9efc964090af17af18c8dc570f451b9e82de775bb9fb8c1414c54a4ba299db12
+  metadata.gz: 2768d0d23733c2d299db6130f9d7d3577ef009aa554d0a3f19d1716403e32020
+  data.tar.gz: 05c46784c97f711bd996620fa66c28ef39e1faf58143087cdad88ee1f9163b14
 SHA512:
-  metadata.gz: b7b9fa6efe358fd8769ab3b16fb7a9c1cbe18bb7330439e9c8c01110c861434cca94df136516d073a5a37b2260887c9d4bdf6c92a7ef92656d6f4a4627486a28
-  data.tar.gz: e2bd9b85b3277938ed6fddf211e9572399165dd8be8d078da6b0ebe48a8870428fa53448e6991f60a040f3141383b754e69272b4eab40e5d4bd425f667c8efbd
+  metadata.gz: d4b55756b6e559e388801d34aeb02a9ad83989d7d247a4e39f3f4af2fae041c8dad97703cb83c8ead91301336f42e9b481e5296a9250223a7edc6b2ce8b0e6df
+  data.tar.gz: b6d8a81d3643bb8937a8dad13360217e9084a8cdf0d9ddf840f70715fea0a94aec0ad72bc27687d046aca83b9f69b61c9866129d6786f40ba723a3e73f4ca3e2

data/.ruby-version

@@ -0,0 +1 @@
+ruby-3.0.7

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.20)
+    patchwork_csv_utils (0.1.22)
 
 GEM
   remote: https://rubygems.org/
@@ -56,6 +56,7 @@ GEM
 PLATFORMS
   arm64-darwin-22
   arm64-darwin-23
+  arm64-darwin-24
   x86_64-linux
 
 DEPENDENCIES

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, 6))?;
-    module.define_singleton_method("transform_csv", function!(transform_csv, 6))?;
+    module.define_singleton_method("to_csv", function!(to_csv, 7))?;
+    module.define_singleton_method("transform_csv", function!(transform_csv, 7))?;
     Ok(())
 }

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

@@ -6,11 +6,14 @@ use std::fs::File;
 
 use crate::utils::{check_mandatory_headers, create_header_map, headers_as_byte_record, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, to_datetime_error, FileExtension};
 
-pub fn transform_csv(ruby: &Ruby, csv_path: String,
-                     target_path: String, exclusions: RArray,
+pub fn transform_csv(ruby: &Ruby,
+                     csv_path: String,
+                     target_path: String,
+                     exclusions: RArray,
                      mandatory_headers: RArray,
                      status_exclusions: RArray,
-                     expected_trust_name: String,) -> magnus::error::Result<()> {
+                     expected_trust_name: String,
+                     is_streamed_file: bool) -> 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()));
     }
@@ -47,7 +50,7 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String,
 
     for (ri, record) in mandatory_records.iter().enumerate() {
 
-        if skip_excluded_rows(request_id, &record, &exclusions) { continue; }
+        if skip_excluded_rows(request_id, &status, &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; }
@@ -60,7 +63,9 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String,
             let column_value = record.get(*column_index).ok_or(missing_value(ruby, column))?;
             let column_value = column_value.trim_end();
 
-            validate_trust_name(ruby, &expected_trust_name, trust_name, i, &column_value.to_string())?;
+            if !is_streamed_file {
+                validate_trust_name(ruby, &expected_trust_name, trust_name, i, &column_value.to_string())?;
+            }
 
             if i == *date {
                 let current = string_to_datetime(column_value).ok_or(to_datetime_error(ruby, column_value, ri, "Date"))?;
@@ -137,7 +142,15 @@ fn get_column_name(inverse_header_map: &HashMap<usize, String>, i: &usize) -> St
     column_name.to_string()
 }
 
-fn skip_excluded_rows(request_id: &usize, r: &StringRecord, exclusions: &Vec<String>) -> bool {
+fn skip_excluded_rows(request_id: &usize, status: &Option<&usize>, r: &StringRecord, exclusions: &Vec<String>) -> bool {
+    if let Some(status_index) = status {
+        if let Some(status) = r.get(**status_index) {
+            if status.eq("Recalled") {
+                return false
+            }
+        }
+    }
+
     let value = r.get(*request_id).unwrap_or_default();
     exclusions.contains(&value.to_string())
 }

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

@@ -2,7 +2,7 @@ use std::collections::HashMap;
 use std::fs::File;
 use std::io::{BufWriter, Write};
 
-use calamine::{open_workbook_auto, Data, Range, Reader};
+use calamine::{open_workbook_auto, Data, DataType, Range, Reader};
 use chrono::{NaiveDateTime, Timelike, Utc};
 use magnus::{RArray, Ruby};
 
@@ -14,6 +14,7 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
               mandatory_headers: RArray,
               status_exclusions: RArray,
               expected_trust_name: String,
+              is_streamed_file: bool
 ) -> magnus::error::Result<()> {
     if !xls_path.has_extension(&["xls","xlsx"]) {
         return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls or xlsx file".to_string()));
@@ -40,7 +41,7 @@ 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, status_exclusions, expected_trust_name)
+    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions, expected_trust_name, is_streamed_file)
 }
 
 fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
@@ -48,7 +49,8 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
                        mandatory_headers: Vec<String>,
                        headers_list: Vec<String>,
                        status_exclusions: Vec<String>,
-                       expected_trust_name: String) -> magnus::error::Result<()> {
+                       expected_trust_name: String,
+                       is_streamed_file: bool) -> 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"))?;
@@ -64,14 +66,17 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
     for (ri, r) in mandatory_rows.into_iter().enumerate() {
         let mut date_value = Utc::now().naive_utc();
 
-        if skip_excluded_rows(&request_id, &r, &exclusions) { continue; }
+        if skip_excluded_rows(&request_id, &status, &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) {
             return Err(magnus::Error::new(ruby.exception_standard_error(), format!("Date value is not present in row: {}", ri)));
         }
-        validate_trust_name(ruby, &expected_trust_name, trust_name, ri, &r)?;
+
+        if !is_streamed_file {
+            validate_trust_name(ruby, &expected_trust_name, trust_name, ri, &r)?;
+        }
 
         for (i, c) in mandatory_headers.iter().enumerate() {
             let column_index = header_map.get(c).ok_or(missing_header(ruby, c))?;
@@ -180,7 +185,17 @@ fn date_value_is_not_present(date: &usize, r: &Vec<&Data>) -> bool {
     r[*date] == &Data::Empty
 }
 
-fn skip_excluded_rows(request_id: &usize, r: &Vec<&Data>, exclusions: &Vec<String>) -> bool {
+fn skip_excluded_rows(request_id: &usize, status: &Option<&usize>, r: &Vec<&Data>, exclusions: &Vec<String>) -> bool {
+    if let Some(status_index) = status {
+        if let Some(status) = r.get(**status_index) {
+            if let Some(status_str) = status.as_string() {
+                if status_str.eq("Recalled") {
+                    return false
+                }
+            }
+        }
+    }
+
     let value = r[*request_id].to_string();
     exclusions.contains(&value.to_string())
 }

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.20'
+  VERSION = '0.1.22'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.20
+  version: 0.1.22
 platform: x86_64-darwin
 authors:
 - kingsley.hendrickse
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2024-12-05 00:00:00.000000000 Z
+date: 2025-07-08 00:00:00.000000000 Z
 dependencies: []
 description: Deduplication of CSV files and XLS to CSV conversion.
 email:
@@ -19,6 +19,7 @@ extra_rdoc_files: []
 files:
 - ".rspec"
 - ".rubocop.yml"
+- ".ruby-version"
 - Cargo.lock
 - Cargo.toml
 - Gemfile