smarter_csv 1.8.2 → 1.8.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 4a6ec6f3a579d9c1e6bfc2c3c9006f64d8c7b705eeca6ec048ea56c688f8ea1c
-  data.tar.gz: ba9a4a289adcc2fc398ae608f9570c28baac57b877852f3ea37c78fa57f2d7e3
+  metadata.gz: 654b04532f0d0b1e15bf84c2e23231e00946a1f57c613f53555ba2d531eaf4f9
+  data.tar.gz: d99a921a908864764a39e94818be45c9feb8a1fbe15eb776e24ef10e98c749fd
 SHA512:
-  metadata.gz: d8f516501a5539e30789e2d18c4d051f50372786d8df1272192c2bc7997470cf5d5e1ae94b776d0d580cb62ed8ffb0f6591ccc2be5d60eae6e421f22f0c92f94
-  data.tar.gz: 2993c59278adb531cf2299c0aa3869c637868f2f4e6421f845e4ade35011f94ee6e226f43e07b206c67c354c2eb38c0a41981ffbdbff00950690b94b06b2aacd
+  metadata.gz: 8005c2b6bdd4e82ab1acc8849afd4b8d7abf0d744bb18fa76aaac68a707a8f14300b4e844abac3dacab24b254c81787dc4501a1cc1138ebdc97fe52728e82f30
+  data.tar.gz: 0baead2aa4d6841f3770e27a24e5dc5d783873db253c8185e81366a2b5a36045d82f4dc2011fbd46373cf434968675b232217c8764c2c858d74c1cceaebd45ed

data/CHANGELOG.md

@@ -1,6 +1,10 @@
 
 # SmarterCSV 1.x Change Log
 
+## 1.8.3 (2023-03-30)
+  * bugfix: windows one-column files were raising NoColSepDetected (issue #229)
+    
+
 ## 1.8.2 (2023-03-21)
   * bugfix: do not raise `NoColSepDetected` for CSV files with only one column in most cases (issue #222)
             If the first lines contain non-ASCII characters, and no col_sep is detected, it will still raise `NoColSepDetected`

data/README.md

@@ -3,26 +3,33 @@
 
  [![codecov](https://codecov.io/gh/tilo/smarter_csv/branch/main/graph/badge.svg?token=1L7OD80182)](https://codecov.io/gh/tilo/smarter_csv) [![Gem Version](https://badge.fury.io/rb/smarter_csv.svg)](http://badge.fury.io/rb/smarter_csv)
  
+#### Development Branches
+
+* default branch is `main` for 1.x development
+* 2.x development is on `2.0-development` (check this branch for 2.0 documentation)
+
 #### Work towards Future Version 2.0
 
 * Work towards SmarterCSV 2.0 is still ongoing, with improved features, and more streamlined options, but consider it as experimental at this time.
   Please check the [2.0-develop branch](https://github.com/tilo/smarter_csv/tree/2.0-develop), open any issues and pull requests with mention of tag v2.0.
 
-* New versions of SmarterCSV 1.x will soon print a deprecation warning if you set :verbose to true
-  See below for list of deprecated options.
+---------------
 
-#### Restructured Branches
+#### SmarterCSV 1.x [Current Version]
 
-* default branch is `main` for 1.x development
-* 2.x development is on `2.0-development`
+`smarter_csv` is a Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, suitable for direct processing with ActiveRecord, parallel processing, kicking-off batch jobs with Sidekiq, or oploading data to S3.
 
----------------
+The goals for SmarterCSV are: 
+  * ease of use for handling most common CSV files without having to tweak options
+  * improve robustness of your code when you have no control over the quality of the CSV files which are processed
+  * formatting each row of data as a hash, in order to allow easy processing with ActiveRecord, parallel processing, kicking-off batch jobs with Sidekiq, or oploading data to S3.
 
-#### SmarterCSV 1.x [Current Version]
+#### Rescue from Exceptions
+While SmarterCSV uses sensible defaults to process the most common CSV files, it will raise exceptions if it can not auto-detect `col_sep`, `row_sep`, or if it encounters other problems. Therefore, when calling `SmarterCSV.process`, please rescue from `SmarterCSVException`, and handle outliers according to your requirements.
 
-`smarter_csv` is a Ruby Gem for smarter importing of CSV Files as Array(s) of Hashes, suitable for direct processing with ActiveRecord, parallel processing, or kicking-off batch jobs with Sidekiq.
+If you encounter unusual CSV files, please follow the tips in the Troubleshooting section below. You can use the options below to accomodate for unusual formats.
 
-To create high-quality output, some options are enabled as a default. Please make sure to check the output and tweak the options accordingly.
+#### Features
 
 One `smarter_csv` user wrote:
 

data/ext/smarter_csv/smarter_csv.c

@@ -15,67 +15,67 @@
 static VALUE rb_parse_csv_line(VALUE self, VALUE line, VALUE col_sep, VALUE quote_char, VALUE max_size) {
   if (RB_TYPE_P(line, T_NIL) == 1) {
     return rb_ary_new();
+  }
 
-  } else if (RB_TYPE_P(line, T_STRING) == 1) {
-    rb_encoding *encoding = rb_enc_get(line); /* get the encoding from the input line */
-    char *startP = RSTRING_PTR(line); /* may not be null terminated */
-    long line_len = RSTRING_LEN(line);
-    char *endP = startP + line_len ; /* points behind the string */
-    char *p = startP;
+  if (RB_TYPE_P(line, T_STRING) != 1) {
+    rb_raise(rb_eTypeError, "ERROR in SmarterCSV.parse_line: line has to be a string or nil");
+  }
 
-    char *col_sepP = RSTRING_PTR(col_sep);
-    long col_sep_len = RSTRING_LEN(col_sep);
+  rb_encoding *encoding = rb_enc_get(line); /* get the encoding from the input line */
+  char *startP = RSTRING_PTR(line); /* may not be null terminated */
+  long line_len = RSTRING_LEN(line);
+  char *endP = startP + line_len ; /* points behind the string */
+  char *p = startP;
 
-    char *quoteP = RSTRING_PTR(quote_char);
-    long quote_count = 0;
+  char *col_sepP = RSTRING_PTR(col_sep);
+  long col_sep_len = RSTRING_LEN(col_sep);
 
-    bool col_sep_found = true;
+  char *quoteP = RSTRING_PTR(quote_char);
+  long quote_count = 0;
 
-    VALUE elements = rb_ary_new();
-    VALUE field;
-    long i;
+  bool col_sep_found = true;
 
-    while (p < endP) {
-      /* does the remaining string start with col_sep ? */
-      col_sep_found = true;
-      for(i=0; (i < col_sep_len) && (p+i < endP) ; i++) {
-        col_sep_found = col_sep_found && (*(p+i) == *(col_sepP+i));
-      }
-      /* if col_sep was found and we have even quotes */
-      if (col_sep_found && (quote_count % 2 == 0)) {
-        /* if max_size != nil && lements.size >= header_size */
-        if ((max_size != Qnil) && RARRAY_LEN(elements) >= NUM2INT(max_size)) {
-          break;
-        } else {
-          /* push that field with original encoding onto the results */
-          field = rb_enc_str_new(startP, p - startP, encoding);
-          rb_ary_push(elements, field);
+  VALUE elements = rb_ary_new();
+  VALUE field;
+  long i;
 
-          p += col_sep_len;
-          startP = p;
-        }
+  while (p < endP) {
+    /* does the remaining string start with col_sep ? */
+    col_sep_found = true;
+    for(i=0; (i < col_sep_len) && (p+i < endP) ; i++) {
+      col_sep_found = col_sep_found && (*(p+i) == *(col_sepP+i));
+    }
+    /* if col_sep was found and we have even quotes */
+    if (col_sep_found && (quote_count % 2 == 0)) {
+      /* if max_size != nil && lements.size >= header_size */
+      if ((max_size != Qnil) && RARRAY_LEN(elements) >= NUM2INT(max_size)) {
+        break;
       } else {
-        if (*p == *quoteP) {
-          quote_count += 1;
-        }
-        p++;
-      }
-    } /* while */
+        /* push that field with original encoding onto the results */
+        field = rb_enc_str_new(startP, p - startP, encoding);
+        rb_ary_push(elements, field);
 
-    /* check if the last part of the line needs to be processed */
-    if ((max_size == Qnil) || RARRAY_LEN(elements) < NUM2INT(max_size)) {
-      /* copy the remaining line as a field with original encoding onto the results */
-      field = rb_enc_str_new(startP, endP - startP, encoding);
-      rb_ary_push(elements, field);
+        p += col_sep_len;
+        startP = p;
+      }
+    } else {
+      if (*p == *quoteP) {
+        quote_count += 1;
+      }
+      p++;
     }
+  } /* while */
 
-    return elements;
+  /* check if the last part of the line needs to be processed */
+  if ((max_size == Qnil) || RARRAY_LEN(elements) < NUM2INT(max_size)) {
+    /* copy the remaining line as a field with original encoding onto the results */
+    field = rb_enc_str_new(startP, endP - startP, encoding);
+    rb_ary_push(elements, field);
   }
 
-  rb_raise(rb_eTypeError, "ERROR in SmarterCSV.parse_line: line has to be a string or nil");
+  return elements;
 }
 
-
 VALUE SmarterCSV = Qnil;
 
 void Init_smarter_csv(void) {

data/lib/smarter_csv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SmarterCSV
-  VERSION = "1.8.2"
+  VERSION = "1.8.3"
 end

data/lib/smarter_csv.rb

@@ -3,8 +3,11 @@
 require_relative "extensions/hash"
 require_relative "smarter_csv/version"
 
-require_relative "smarter_csv/smarter_csv" unless ENV['CI'] # does not compile/link in CI?
-# require 'smarter_csv.bundle' unless ENV['CI'] # local testing
+if `uname -s`.chomp == 'Darwin'
+  require 'smarter_csv.bundle' unless ENV['CI'] # local testing
+else
+  require_relative "smarter_csv/smarter_csv" unless ENV['CI'] # does not compile/link in CI?
+end
 
 module SmarterCSV
   class SmarterCSVException < StandardError; end
@@ -411,7 +414,7 @@ module SmarterCSV
 
       if candidates.values.max == 0
         # if the header only contains
-        return ',' if line =~ /^\w+$/
+        return ',' if line.chomp(options[:row_sep]) =~ /^\w+$/
 
         raise SmarterCSV::NoColSepDetected
       end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: smarter_csv
 version: !ruby/object:Gem::Version
-  version: 1.8.2
+  version: 1.8.3
 platform: ruby
 authors:
 - Tilo Sloboda
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-03-22 00:00:00.000000000 Z
+date: 2023-03-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: awesome_print