berkeley_library-tind 0.5.1 → 0.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 24232cda73f63d90367c05453c325f468d6103d667e820671f19c251cabd3814
-  data.tar.gz: 98d09880d886d8f351f0a038b8513aefe5dfe5c3a72108f634d79f7ad2485506
+  metadata.gz: ade606682d0d814a4debfbe0be2a6741ae72977d710511d5df70118569dea764
+  data.tar.gz: 2da4f7cd4b7f0c1cf6f8dcf9bf3346d89599e9130f28a185cb0cab0a37a39d3d
 SHA512:
-  metadata.gz: 15c2560d8bee4b55fbb66a51f101afd731ef02bf542c7e4433ea0b095efa492a9b7429a7bb8929226079bb24a40a9f5e27432c6c855812a0a29d913d6877958e
-  data.tar.gz: 6133181a93ef7a1204e6c73ea56a5fdee80f40817bfbe87c3c03ed063ec070e8c6f50dff732bbd987e30b929c14ba6e0b056a0b259f8327273f24e7048a069dc
+  metadata.gz: ed708269e8c628616c89643c49cb3394401febf8f9a0f4defde88abad17a8ac2f5b43663345cd0513aa2e7b02e41fb3475446f55aa7ad394aa83ad62ae114565
+  data.tar.gz: b4f851305ad936b9f7cb46c8a521358cdfff34f51aebfb6d121481545777476af8adce6c3b8c0042aeaeca2ee00a7d1826f955f46ee5ad1f11361c7ed1843b72

data/.github/workflows/build.yml

@@ -10,9 +10,21 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     steps:
-      - uses: actions/checkout@v2
-      - uses: ruby/setup-ruby@v1
+      - name: Check out repository
+        uses: actions/checkout@v2
+
+      - name: Set up Ruby
+        uses: ruby/setup-ruby@v1
         with:
           ruby-version: ${{ matrix.ruby }}
           bundler-cache: true # runs 'bundle install' and caches installed gems automatically
-      - run: bundle exec rake
+
+      - name: Run checks
+        run: bundle exec rake
+
+      - name: Upload artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v3
+        with:
+          name: artifacts
+          path: artifacts/**

data/.gitignore

@@ -7,6 +7,9 @@
 # Additional IDEA/RubyMine ignores
 .idea/.rakeTasks
 
+# Visual Studio Code ignores
+.vscode
+
 # Don't commit Gemfile.lock for libraries
 Gemfile.lock
 

data/.idea/inspectionProfiles/Project_Default.xml

@@ -10,6 +10,14 @@
     <inspection_tool class="LanguageDetectionInspection" enabled="false" level="WARNING" enabled_by_default="false" />
     <inspection_tool class="Rubocop" enabled="false" level="WARNING" enabled_by_default="false" />
     <inspection_tool class="RubyCaseWithoutElseBlockInspection" enabled="false" level="WARNING" enabled_by_default="false" />
+    <inspection_tool class="RubyClassMethodNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyClassModuleNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyClassVariableNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyConstantNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyGlobalVariableNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyInstanceMethodNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyInstanceVariableNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyLocalVariableNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
     <inspection_tool class="RubyMismatchedArgumentType" enabled="true" level="WARNING" enabled_by_default="true">
       <option name="myCheckNilability" value="false" />
     </inspection_tool>
@@ -28,6 +36,8 @@
     <inspection_tool class="RubyMismatchedVariableType" enabled="true" level="WARNING" enabled_by_default="true">
       <option name="myCheckNilability" value="false" />
     </inspection_tool>
+    <inspection_tool class="RubyNilAnalysis" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+    <inspection_tool class="RubyParameterNamingConvention" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
     <inspection_tool class="RubyStringKeysInHashInspection" enabled="true" level="INFORMATION" enabled_by_default="true" />
     <inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
       <option name="processCode" value="true" />

data/.idea/tind.iml

@@ -15,6 +15,7 @@
     <orderEntry type="library" scope="PROVIDED" name="addressable (v2.8.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="amazing_print (v1.4.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="ast (v2.4.2, RVM: ruby-2.7.5) [gem]" level="application" />
+    <orderEntry type="library" scope="PROVIDED" name="berkeley_library-alma (v0.0.4, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="berkeley_library-logging (v0.2.6, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="berkeley_library-marc (v0.3.1, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="berkeley_library-util (v0.1.1, RVM: ruby-2.7.5) [gem]" level="application" />
@@ -39,7 +40,7 @@
     <orderEntry type="library" scope="PROVIDED" name="http-cookie (v1.0.4, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="i18n (v1.10.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="ice_nine (v0.11.2, RVM: ruby-2.7.5) [gem]" level="application" />
-    <orderEntry type="library" scope="PROVIDED" name="lograge (v0.11.2, RVM: ruby-2.7.5) [gem]" level="application" />
+    <orderEntry type="library" scope="PROVIDED" name="lograge (v0.12.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="loofah (v2.15.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="marc (v1.1.1, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="method_source (v1.0.0, RVM: ruby-2.7.5) [gem]" level="application" />
@@ -47,7 +48,7 @@
     <orderEntry type="library" scope="PROVIDED" name="mime-types-data (v3.2022.0105, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="minitest (v5.15.0, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="netrc (v0.11.0, RVM: ruby-2.7.5) [gem]" level="application" />
-    <orderEntry type="library" scope="PROVIDED" name="nokogiri (v1.13.1, RVM: ruby-2.7.5) [gem]" level="application" />
+    <orderEntry type="library" scope="PROVIDED" name="nokogiri (v1.13.3, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="oj (v3.13.11, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="ougai (v1.9.1, RVM: ruby-2.7.5) [gem]" level="application" />
     <orderEntry type="library" scope="PROVIDED" name="parallel (v1.21.0, RVM: ruby-2.7.5) [gem]" level="application" />
@@ -110,7 +111,7 @@
           </RakeTaskImpl>
           <RakeTaskImpl description="Run all specs in spec directory, with coverage" fullCommand="coverage" id="coverage" />
           <RakeTaskImpl description="Run tests, check test coverage, check code style, check for vulnerabilities, build gem" fullCommand="default" id="default" />
-          <RakeTaskImpl description="Build berkeley_library-tind.gemspec as berkeley_library-tind-0.4.3.gem" fullCommand="gem" id="gem" />
+          <RakeTaskImpl description="Build berkeley_library-tind.gemspec as berkeley_library-tind-0.6.0.gem" fullCommand="gem" id="gem" />
           <RakeTaskImpl description="Run RuboCop with auto-correct, and output results to console" fullCommand="ra" id="ra" />
           <RakeTaskImpl description="Run rubocop with HTML output" fullCommand="rubocop" id="rubocop" />
           <RakeTaskImpl id="rubocop">

data/CHANGES.md

@@ -1,3 +1,9 @@
+# 0.6.0 (2023-04-06)
+
+- Adds `BerkeleyLibrary::TIND::Mapping` module to map MARC records from Alma to TIND.
+- `BerkeleyLibrary::TIND::MARC::XMLWriter` now assumes that any object that response to `:write`
+  and `:close` is suffiently `IO`-like to write to.
+
 # 0.5.1 (2023-03-23)
 
 - Fix an issue where `BerkeleyLibrary::TIND::MARC::XMLWriter` would drop fields with nonstandard tags (e.g. `FFT` fields)

data/README.md

@@ -30,7 +30,7 @@ To access the TIND API, you will need to set:
    it a "key", so that's the term we use here.)
 
 These can be set directly, via accessors in the `BerkeleyLibrary::TIND::Config` module;
-if they are not set, a value will be read from the environment, and if no 
+if they are not set, a value will be read from the environment, and if no
 value is present in the environment and Rails is loaded, from the Rails
 application configuration (`Rails.application.config`).
 
@@ -43,9 +43,18 @@ application configuration (`Rails.application.config`).
 object, but will always be returned as a `URI` object, and an invalid
 string setting will raise `URI::InvalidURIError`.
 
+### Alma configuration
+
+When mapping Alma records to TIND (see below), this gem uses 
+[`berkeley_library-alma`](https://github.com/BerkeleyLibrary/alma) to load
+Alma records. The scripts in the `bin` directory use the default Alma
+configuration; see the `berkeley_library-alma` 
+[README](https://github.com/BerkeleyLibrary/alma#configuration) for
+details.
+
 ## Command-line tool: `tind-export`
 
-The `tind-export` command allows you to list TIND collections, or to 
+The `tind-export` command allows you to list TIND collections, or to
 export a TIND collection from the command line. (If the gem is installed,
 `tind-export` should be in your `$PATH`. If you've cloned the gem source,
 you can invoke it with `bin/tind-export` from the project root directory.)
@@ -85,3 +94,113 @@ For the full list of options, type `tind-export --help`. Note that you can set
 the TIND base URL and API key either via the environment, as above, or as options
 passed to the `tind-export` command. If both an explicit option and an environment
 variable are set for either, the explicit option takes precedence.
+
+## Mapping MARC records from Alma to TIND
+
+### Transforming Class:
+
+1. BerkeleyLibrary::TIND::Mapping::AlmaSingleTIND    (Transforming one Alma record => One TIND record)
+2. BerkeleyLibrary::TIND::Mapping::AlmaMultipleTIND  (Transforming one Alma record => Multiple TIND records)
+
+### Source of TIND fields
+
+1. Mapped from an Alma record (automatically)
+
+2. Derived from collection information, mms_id, and date (automatically)
+
+    - 336$a
+    - 852$c
+    - 980$a
+    - 982$a,$b
+    - 991$a - (optional)
+    - 902$d
+    - 901$m
+    - 85641$u,$y
+
+3. Added at the time of transforming TIND record (fields of a collection or its record)
+
+    - FFT
+    - 035$a
+    - 998$a
+    - ...
+
+### Example
+
+1. Setup collection information
+   
+   - 336:  type of resource
+   - 852:  collection's repository name
+   - 980:  collection's 980 value
+   - 982:  collection's short name and long name
+   - 991:  collection' restricted name (optional)
+
+``` ruby
+
+def setup_collection
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.collection_parameter_hash = {
+    '336' => ['Image'],
+    '852' => ['East Asian Library'],
+    '980' => ['pre_1912'],
+    '982' => ['Pre 1912 Chinese Materials - short name', 'Pre 1912 Chinese Materials - long name'],
+    '991' => []
+  }
+  
+  # BerkeleyLibrary::TIND::Mapping::AlmaBase.is_035_from_mms_id = true  
+
+  # Flag on getting Alma record using Barcode
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.is_barcode = true           
+end
+```
+
+2. Praparing additional fields
+
+    Adding field using:
+    -  field methods from module:  BerkeleyLibrary::TIND::Mapping::TindField
+    -  Or the original method from Ruby Marc when field method found in above module  
+        ::MARC::DataField.new(tag, indicator1, indicator, [code1, value1], [code2, value2] ...)
+
+```ruby
+
+def additional_tind_fields_1
+  txt = 'v001_0064'
+  url = 'https://digitalassets.lib.berkeley.edu/pre1912ChineseMaterials/ucb/ready/991032333019706532/991032333019706532_v001_0064.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+
+  f = ::MARC::DataField.new('998', ' ', ' ', ['a', 'fake-value'])
+  [fft] << f
+end
+
+def additional_tind_fields_2
+  txt = 'v001_0065'
+  url = 'https://digitalassets.lib.berkeley.edu/pre1912ChineseMaterials/ucb/ready/991032333019706532/991032333019706532_v001_0065.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+  [fft]
+end
+```
+
+3. Transforming one Alma record => One TIND record
+
+```ruby
+setup_collection
+
+# id can be  1)mms_id;  2)Millennium no ; or 3)Barcode
+id = 'C084093187'
+
+alma_tind = BerkeleyLibrary::TIND::Mapping::AlmaSingleTIND.new
+tind_record = alma_tind.record(id, additional_tind_fields_1)
+```
+
+
+4. Or transforming one Alma record => Multiple TIND records
+
+``` ruby
+setup_collection
+
+# id can be 1) mms_id; 2) Millennium bib number; or 3) Item barcode
+# id = '991085821143406532'
+id = 'C084093187'
+
+alma_tind = BerkeleyLibrary::TIND::Mapping::AlmaMultipleTIND.new(id)
+tind_record_1 = alma_tind.record(additional_tind_fields_1)
+tind_record_2 = alma_tind.record(additional_tind_fields_2)
+```

data/berkeley_library-tind.gemspec

@@ -23,6 +23,7 @@ Gem::Specification.new do |spec|
 
   spec.required_ruby_version = ruby_version
 
+  spec.add_dependency 'berkeley_library-alma', '~> 0.0.1'
   spec.add_dependency 'berkeley_library-logging', '~> 0.2'
   spec.add_dependency 'berkeley_library-marc', '~> 0.3.0', '>= 0.3.1'
   spec.add_dependency 'berkeley_library-util', '~> 0.1'

data/bin/alma-multiple-tind

@@ -0,0 +1,50 @@
+#!/usr/bin/env ruby
+
+begin
+  # This should work if (1) the gem is installed, or
+  # (2) we're in development and used `bundle exec`
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+rescue LoadError
+  # If we're in development, `require 'bundler/setup'`
+  # is roughly equivalent to `bundle exec`
+  require 'bundler/setup'
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+end
+
+def setup
+  # set collection name information
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.collection_parameter_hash = {
+    '336' => ['Image'],
+    '852' => ['East Asian Library'],
+    '980' => ['pre_1912'],
+    '982' => ['Pre 1912 Chinese Materials - short name', 'Pre 1912 Chinese Materials - long name'],
+    '991' => []
+  }
+
+  # flag: set it to true if using barcode getting Alma record; default is false
+  # BerkeleyLibrary::TIND::Mapping::AlmaBase.is_barcode = true
+end
+
+def additional_tind_fields
+  txt = 'v001_0064'
+  url = 'https://digitalassets.lib.berkeley.edu/pre1912ChineseMaterials/ucb/ready/991032333019706532/991032333019706532_v001_0064.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+  datafields = [fft]
+
+  f_035 = BerkeleyLibrary::TIND::Mapping::TindField.f_035_from_alma_id('pre_1912', '991085821143406532')
+  datafields << f_035
+end
+
+###########  Use this, when creating multiple TIND records from a single Alma record  ############
+alma_id = '991085821143406532'
+# alma_id = '99108582114340653'  # a bad alma_id
+# alma_id = '991084606989706532' # Host histrical record
+
+setup
+
+BerkeleyLibrary::Alma::Config.default!
+alma_multiple_tind = BerkeleyLibrary::TIND::Mapping::AlmaMultipleTIND.new(alma_id)
+tind_record = alma_multiple_tind.record(additional_tind_fields)
+alma_multiple_tind.save_tind_record_to_file(tind_record, 'tmp/multiple.xml')

data/bin/alma-single-tind

@@ -0,0 +1,48 @@
+#!/usr/bin/env ruby
+
+begin
+  # This should work if (1) the gem is installed, or
+  # (2) we're in development and used `bundle exec`
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+rescue LoadError
+  # If we're in development, `require 'bundler/setup'`
+  # is roughly equivalent to `bundle exec`
+  require 'bundler/setup'
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+end
+
+def setup
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.collection_parameter_hash = {
+    '336' => ['Image'],
+    '852' => ['East Asian Library'],
+    '980' => ['pre_1912'],
+    '982' => ['Pre 1912 Chinese Materials - short name', 'Pre 1912 Chinese Materials - long name'],
+    '991' => []
+  }
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.is_035_from_mms_id = true
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.is_barcode = false
+end
+
+def additional_tind_fields
+  txt = 'v001_0064'
+  url = 'https://digitalassets.lib.berkeley.edu/pre1912ChineseMaterials/ucb/ready/991032333019706532/991032333019706532_v001_0064.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+  f = ::MARC::DataField.new('998', ' ', ' ', ['a', 'fake-value'])
+  [fft] << f
+end
+
+############## Use this, when creating a TIND record from each Alma record ############
+# alma_id = '991085821143406532'
+# alma_id_bad = '99108582114340653' # a bad alma_id
+# alma_id_not_qualified = '991084606989706532' # Host historical record
+barcode = 'C084093187'
+
+id = barcode
+setup
+
+BerkeleyLibrary::Alma::Config.default!
+alma_single_tind = BerkeleyLibrary::TIND::Mapping::AlmaSingleTIND.new
+tind_record = alma_single_tind.record(id, additional_tind_fields)
+alma_single_tind.save_tind_record_to_file(id, tind_record, 'tmp/test_single.xml')

data/bin/save_tind_records

@@ -0,0 +1,80 @@
+#!/usr/bin/env ruby
+
+begin
+  # This should work if (1) the gem is installed, or
+  # (2) we're in development and used `bundle exec`
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+rescue LoadError
+  # If we're in development, `require 'bundler/setup'`
+  # is roughly equivalent to `bundle exec`
+  require 'bundler/setup'
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+end
+
+def setup
+  BerkeleyLibrary::TIND::Mapping::AlmaBase.collection_parameter_hash = {
+    '336' => ['Image'],
+    '852' => ['Bioscience, Natural Resources & Public Health Library'],
+    '980' => ['Forestry'],
+    '982' => ['Forestry', 'Forestry'],
+    '991' => []
+  }
+
+  # BerkeleyLibrary::TIND::Mapping::AlmaBase.is_barcode = true
+end
+
+def fake_additional_tind_fields1
+  fields = []
+  txt = '001'
+  url = 'https://digitalassets.lib.berkeley.edu/forestry/ucb/images/b142086125_i180839998/b142086125_i180839998_001.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+  f_998 = ::MARC::DataField.new('998', ' ', ' ', ['a', 'fake-value'])
+  f_035 = BerkeleyLibrary::TIND::Mapping::TindField.f_035('b142086125')
+  fields << f_998
+  fields << f_035
+  fields << fft
+end
+
+def fake_additional_tind_fields2
+  fields = []
+  txt = '002'
+  url = 'https://digitalassets.lib.berkeley.edu/forestry/ucb/images/b142086125_i180839998/b142086125_i180839998_002.jpg'
+  fft = BerkeleyLibrary::TIND::Mapping::TindField.f_fft(url, txt)
+
+  f_998 = ::MARC::DataField.new('998', ' ', ' ', ['a', 'fake-value'])
+
+  f_035 = BerkeleyLibrary::TIND::Mapping::TindField.f_035('b142107827')
+  fields << f_998
+  fields << f_035
+  fields << fft
+end
+
+def tind_records
+  records = []
+  alma_tind = BerkeleyLibrary::TIND::Mapping::AlmaSingleTIND.new
+
+  record1 = alma_tind.record('b142086125', fake_additional_tind_fields1)
+  record2 = alma_tind.record('b142107827', fake_additional_tind_fields2)
+  records << record1
+  records << record2
+end
+
+def save_batch(file, with_tind_xmlwritter)
+  setup
+  writer = ::MARC::XMLWriter.new(file)
+  writer = BerkeleyLibrary::TIND::MARC::XMLWriter.new(file) if with_tind_xmlwritter
+
+  tind_records.each do |record|
+    record.leader = nil if with_tind_xmlwritter
+    writer.write(record)
+  end
+  writer.close
+end
+
+# save with tind xmlwritter
+save_batch('tmp/test_tind_xmlwritter.xml', true)
+
+# save with Marc xmlwritter
+save_batch('tmp/test_marc_xmlwritter.xml', false)

data/bin/tind-marc

@@ -0,0 +1,73 @@
+#!/usr/bin/env ruby
+
+begin
+  # This should work if (1) the gem is installed, or
+  # (2) we're in development and used `bundle exec`
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+rescue LoadError
+  # If we're in development, `require 'bundler/setup'`
+  # is roughly equivalent to `bundle exec`
+  require 'bundler/setup'
+  require 'berkeley_library/tind'
+  require 'berkeley_library/alma'
+end
+
+# 1. get Alma record
+BerkeleyLibrary::Alma::Config.default!
+# oskicat_num = 'b11082434'
+# alma_num = '991011084939706532'
+# alma no 880 field
+alma_num = '991085821143406532'
+
+# alma no 880 field
+# alma_num =  '991039355849706532'
+record_id = BerkeleyLibrary::Alma::RecordId.parse(alma_num)
+oskicat_record = record_id.get_marc_record
+
+# 2. get collection information fields
+# This information from "collection name" table on share driver
+collection_parameters = {
+  '336' => ['Image'],
+  '852' => ['East Asian Library'],
+  '980' => ['pre_1912'],
+  '982' => ['Pre 1912 Chinese Materials', 'Pre 1912 Chinese Materials'],
+  '991' => []
+}
+
+collection_tind_fields = BerkeleyLibrary::TIND::Mapping::ExternalTindField.tind_fields_from_collection_information(collection_parameters)
+
+# 3. get other external tind fields
+other_external_tind_fields = []
+tind_fields_from_alma_id = BerkeleyLibrary::TIND::Mapping::ExternalTindField.tind_mms_id_fields('991011084939706532')
+
+other_external_tind_fields.concat tind_fields_from_alma_id
+
+# 4. get fft fields
+
+new_subfield1 = BerkeleyLibrary::TIND::Mapping::Util.subfield('a', 'https://digitalassets.lib.berkeley.edu/pre1912ChineseMaterials/ucb/ready/991032333019706532/991032333019706532_v001_0064.jpg')
+new_subfield2 = BerkeleyLibrary::TIND::Mapping::Util.subfield('d', 'v001_0064')
+fft_datafield = BerkeleyLibrary::TIND::Mapping::Util.datafield('FFT', [' ',  ' '], [new_subfield1, new_subfield2])
+ffts = [fft_datafield]
+
+# 5. put all external tind fields together
+external_tind_fields = collection_tind_fields
+external_tind_fields.concat other_external_tind_fields
+external_tind_fields.concat ffts
+
+# 6. create tind-marc object,
+tindmarc = BerkeleyLibrary::TIND::Mapping::TindMarc.new(oskicat_record)
+
+# 7. add external tind fields(these tind fields will paticipate in "additional process")
+tindmarc.tind_external_datafields = external_tind_fields
+
+##### output ####
+# 8. Get tind fields mapped from alma
+# tindmarc.tindfields
+
+# 9. get a tind record which including external tind fields
+# tindmarc.tind_record
+
+# 10. save the tind record to an xml file
+
+tindmarc.save('tmp/test.xml')

data/lib/berkeley_library/tind/mapping/additional_datafield_process.rb

@@ -0,0 +1,128 @@
+# 1. Combine repeated fields
+# 2. Remove characters pre_defined
+module BerkeleyLibrary
+  module TIND
+    module Mapping
+      module AdditionalDatafieldProcess
+
+        # process 1: remove and combine repeated fields - defined in Config module
+        def remove_repeats(fields)
+          Config.no_duplicated_tags.each { |tag| remove_repeated_fields(tag, fields) }
+          fields
+        end
+
+        # process 2: remove charaters in subfields defined in Config module
+        def clean_subfields(fields)
+          fields.each do |f|
+            next unless field_in_tags?(f, Config.clean_tags)
+
+            clean_subfields_in_field(f)
+          end
+          fields
+        end
+
+        # 1. Find all datafield with the tag,
+        #    if more than one found, combine repeated datafields which have a same tag into one
+        # 2. Find all 880 datafields with subfield6 referring to the tag,
+        #    if more than one found, combine repeated datafields with one subfield 6,
+        #    a related datafield will be modified to have the same sequence in subfield 6 as in this 880 subfield 6
+        def remove_repeated_fields(tag, fields)
+          repeated_fields = fields_on_tag(tag, fields)
+          remove_repeated(repeated_fields, fields)
+
+          repeated_880_fields = fields_880_on_subfield6_referredtag(tag, fields)
+          remove_repeated(repeated_880_fields, fields)
+          fields
+        end
+
+        # clean subfields of a datafield
+        def clean_subfields_in_field(field)
+          field.subfields.each { |sf| clean_subfield(sf) }
+        end
+
+        private
+
+        def field_in_tags?(field, tags)
+          tag = field.tag
+          tag_to_match = tag == '880' ? referred_tag(field) : tag
+          return false unless tag_to_match
+
+          tags.include? tag_to_match
+        end
+
+        def fields_on_tag(tag, fields)
+          fields.select { |f| f.tag == tag }
+        end
+
+        def fields_880_on_subfield6_referredtag(tag, fields)
+          fields.select { |f| field_880_has_referred_tag?(tag, f) }
+        end
+
+        # Marc with tag in 'Config.no_duplicated_tags' are not supposed to have the same multiple subfields
+        # but sometime, sourc data error happens
+        # solution:
+        # taking the first subfield 6
+        # taking the first other subfield when there are multiple same subfields
+        # if 880 and regular field having unmatching subfield 6 in sequnce number, they will go to log file
+        # A user will check the log and correct data in Alma or TIND accordingly
+        def combined_subfields(fields)
+          sf_arr = []
+          subfield_6 = the_first_subfield6(fields)
+          sf_arr << subfield_6 if subfield_6
+          identical_subfields = no_duplicated_first_subfields(fields)
+          sf_arr.concat identical_subfields
+          sf_arr
+        end
+
+        # if there are multiple same subfields, pick up the first one, ignore the others
+        def no_duplicated_first_subfields(fields)
+          indentical_subfields = []
+
+          fields.each do |f|
+            subfields = subfields_without_subfield6(f)
+            subfields.each { |sf| indentical_subfields << sf if not_in_identical_subfields?(indentical_subfields, sf) }
+          end
+
+          indentical_subfields
+        end
+
+        def subfield_codes(subfields)
+          subfields.map(&:code)
+        end
+
+        def not_in_identical_subfields?(subfields, subfield)
+          !subfield_codes(subfields).include? subfield.code
+        end
+
+        # return a combined datafield from repeated datafields - with the same tag
+        def identical_field(repeated_fields)
+          tag = repeated_fields[0].tag
+          indicator = first_indicator(repeated_fields)
+          subfield_arr = combined_subfields(repeated_fields)
+          Util.datafield(tag, indicator, subfield_arr)
+        end
+
+        # remove repeated fields
+        def rm_fields(fields_tobe_removed, fields)
+          fields.delete_if { |f| fields_tobe_removed.include? f }
+        end
+
+        # suppose all repeated datafield have the same indictor
+        def first_indicator(fields)
+          indicator1 = fields[0].indicator1
+          indicator2 = fields[0].indicator2
+          [indicator1, indicator2]
+        end
+
+        # remove and keep one repeated datafield
+        def remove_repeated(repeated_fields, fields)
+          return fields unless repeated_fields.length > 1
+
+          rm_fields(repeated_fields, fields)
+          fields << identical_field(repeated_fields)
+          fields
+        end
+      end
+    end
+  end
+end