patchwork_csv_utils 0.1.3-x86_64-darwin → 0.1.5-x86_64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f379c95f12fb3cbdaec54611a51abb6c15393a275e898701abde6536b5eb894c
-  data.tar.gz: 22f9b467cdc5b5b5bcad81394344fe838e03eecf3891f4b6d683199cc828760d
+  metadata.gz: 53bd775b8a062a5418959e170dce922799739ebbf4a4845eb48f65e889ae4fff
+  data.tar.gz: 26e9f478dd57a8a9307b4536e242af967145c688ae9e4f4002655da86f8405cc
 SHA512:
-  metadata.gz: 3a07e333b63530ebc3186f0776ce6ba1921344bc352587ee713b232fef95553bd7be8a2c52961c5ffc036308c00e4daea4e5884dbd74dbb002e32aaac03e1c06
-  data.tar.gz: 29cd28bc6bc51bef21d088308147b037484ef90542d8d3df225b673a4c6c1e91f1bd0380a04d1e52d61dfa711953c690e4d8e9049a524be62a055c42ae650c26
+  metadata.gz: 256012cce7a6b5802c9ab05fe1e9063e7d99f63fa83f3f011f8375698a5abb1897312776c333fd9757e17c20b7674aff9b9997c3519effb39f9833be2be3f8e9
+  data.tar.gz: 6ce45dcb2f95347350f6272fc8b0c4b84e0b8d24bd773d86b40e9b370de334839773c2363be1ef55e6809d6f510f19bfd25ebecdc669dd65dbb61a8aaa91b172

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.3)
+    patchwork_csv_utils (0.1.5)
 
 GEM
   remote: https://rubygems.org/

data/ext/csv_utils/src/lib.rs

@@ -8,6 +8,6 @@ pub mod utils;
 fn init() -> Result<(), magnus::Error> {
     let module = define_module("CsvUtils")?;
     module.define_singleton_method("dedup", function!(dedup, 3))?;
-    module.define_singleton_method("to_csv", function!(to_csv, 3))?;
+    module.define_singleton_method("to_csv", function!(to_csv, 2))?;
     Ok(())
 }

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

@@ -33,12 +33,20 @@ pub fn dedup(ruby: &Ruby, previous_csv_path: String, new_csv_path: String, targe
     let mut previous_records = vec![];
     for previous_record in previous_csv.records() {
         let previous_record = previous_record.map_err(|e| magnus_err(ruby, e, "previous_record"))?;
+
+        if has_empty_row_skip(&previous_record) { continue; }
+        if has_empty_first_col_skip_row(&previous_record) { continue; }
+
         let previous_record = previous_record.into_iter().map(|r| r.trim_end()).collect::<StringRecord>();
         previous_records.push(previous_record)
     }
 
     for new_record in new_csv.records() {
         let new_record = new_record.map_err(|e| magnus_err(ruby, e, "new_record"))?;
+
+        if has_empty_row_skip(&new_record) { continue; }
+        if has_empty_first_col_skip_row(&new_record) { continue; }
+
         let new_record = new_record.into_iter().map(|r| r.trim_end()).collect::<StringRecord>();
         if !previous_records.contains(&new_record) {
             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
     Ok(())
 }
 
+fn has_empty_first_col_skip_row(previous_record: &StringRecord) -> bool {
+    if previous_record[0].is_empty() {
+        return true;
+    }
+    false
+}
+
+fn has_empty_row_skip(record: &StringRecord) -> bool {
+    if record.iter().all(|r| r.is_empty()) {
+        return true;
+    }
+    false
+}
+
 

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

@@ -8,13 +8,15 @@ use magnus::Ruby;
 
 use crate::utils::{FileExtension, magnus_err};
 
-pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String, sheet_name: String) -> magnus::error::Result<()> {
+pub fn to_csv(ruby: &Ruby, xls_path: String, target_path: String) -> 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()));
     }
 
     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(sheet_name.as_str()).map_err(|e| magnus_err(ruby, e, "Error"))?;
+    let range = workbook.worksheet_range_at(0)
+        .ok_or(magnus::Error::new(ruby.exception_standard_error(), "no worksheet found in xls".to_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 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
     for (ri, r) in range.rows().enumerate() {
         let mut date_value = Utc::now().naive_utc();
 
-        if r.iter().all(|c| c == &Data::Empty) {
-            continue;
-        }
+        if skip_empty_rows(r) { continue; }
+        if skip_rows_with_no_request_id(&header_map, r) { continue; }
 
-        for (i, c) in r.iter().enumerate() {
-            let date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
-            let start = header_map.get("Start").ok_or(missing_header(ruby, "Start"))?;
-            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 date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
+        let start = header_map.get("Start").ok_or(missing_header(ruby, "Start"))?;
+        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"))?;
 
+        for (i, c) in r.iter().enumerate() {
             match *c {
                 Data::Empty => Ok(()),
                 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
     Ok(())
 }
 
+fn skip_empty_rows(r: &[Data]) -> bool {
+    if r.iter().all(|c| c == &Data::Empty) {
+        return true;
+    }
+    false
+}
+
+fn skip_rows_with_no_request_id(header_map: &HashMap<String, usize>, r: &[Data]) -> bool {
+    if let Some(request_id) = header_map.get("Request Id") {
+        if r[*request_id] == Data::Empty {
+            return true;
+        }
+    }
+    false
+}
+
 fn missing_header(ruby: &Ruby, header: &str) -> magnus::Error {
     magnus::Error::new(ruby.exception_standard_error(), format!("Missing '{}' header in xls", header))
 }

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.3'
+  VERSION = '0.1.5'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.1.5
 platform: x86_64-darwin
 authors:
 - kingsley.hendrickse