test_pm25_yearly_download.cwl

  1#!/usr/bin/env cwl-runner
  2### Test harness for pm25_yearly_download.cwl
  3
  4cwlVersion: v1.2
  5class: Workflow
  6
  7requirements:
  8  InlineJavascriptRequirement: {}
  9  MultipleInputFeatureRequirement: {}
 10  ScatterFeatureRequirement: {}
 11  StepInputExpressionRequirement: {}
 12  SubworkflowFeatureRequirement: {}
 13
 14
 15# All inputs of original pipeline, remove what is not needed
 16inputs:
 17  component:
 18    default:
 19    - BC
 20    - NH4
 21    - NIT
 22    - OM
 23    - SO4
 24    - SOIL
 25    - SS
 26    doc: "Optional components provided as percentages in a separate set \nof netCDF\
 27      \ files\n"
 28    type: string[]
 29  connection_name:
 30    doc: 'The name of the section in the database.ini file or a literal
 31
 32      `None` to skip over database ingestion step
 33
 34      '
 35    type: string
 36  database:
 37    doc: "Path to database connection file, usually database.ini. \nThis argument\
 38      \ is ignored if `connection_name` == `None`\n"
 39    type: File
 40  downloads:
 41    doc: "Local or AWS bucket folder containing netCDF grid files, downloaded \nand\
 42      \ unpacked from Washington University in St. Louis (WUSTL) Box\nsite. Annual\
 43      \ and monthly data repositories are described in\n[WUSTL Atmospheric Composition\
 44      \ Analysis Group](https://sites.wustl.edu/acag/datasets/surface-pm2-5/).\n\n\
 45      The annual data for PM2.5 is also available in \na Harvard URC AWS Bucket: `s3://nsaph-public/data/exposures/wustl/`\n"
 46    type: Directory
 47  geography:
 48    doc: 'Type of geography: zip codes or counties
 49
 50      Supported values: "zip", "zcta" or "county"
 51
 52      '
 53    type: string
 54  proxy:
 55    default: ''
 56    doc: HTTP/HTTPS Proxy if required
 57    type: string?
 58  ram:
 59    default: 2GB
 60    doc: Runtime memory, available to the process
 61    type: string
 62  shape_file_collection:
 63    default: tiger
 64    doc: "[Collection of shapefiles](https://www2.census.gov/geo/tiger), \neither\
 65      \ GENZ or TIGER\n"
 66    type: string
 67  strategy:
 68    default: auto
 69    doc: 'Rasterization strategy, see
 70
 71      [documentation](https://foromeplatform.github.io/dorieh/strategy.html)
 72
 73      for the list of supported values and explanations
 74
 75      '
 76    type: string
 77  table:
 78    default: pm25_aggregated
 79    doc: The name of the table to store teh aggregated data in
 80    type: string
 81  test_script:
 82    doc: File containing SQL test script
 83    type: File
 84  variable:
 85    default: PM25
 86    doc: 'The main variable that is being aggregated over shapes. We have tested
 87
 88      the pipeline for PM25
 89
 90      '
 91    type: string
 92  years:
 93    default:
 94    - 2009
 95    - 2010
 96    type: int[]
 97
 98
 99steps:
100  execute:
101    run: pm25_yearly_download.cwl
102    in:
103      proxy: proxy
104      downloads: downloads
105      geography: geography
106      years: years
107      variable: variable
108      component: component
109      strategy: strategy
110      ram: ram
111      shape_file_collection: shape_file_collection
112      database: database
113      connection_name: connection_name
114      table: table
115    out:
116      - aggregate_data
117      - data_dictionary
118      - consolidated_data
119      - shapes
120      - aggregate_log
121      - aggregate_err
122      - ingest_log
123      - index_log
124      - vacuum_log
125      - ingest_err
126      - index_err
127      - vacuum_err
128
129  verify:
130    run: run_test.cwl
131    in:
132      database: database
133      connection_name: connection_name
134      script: test_script
135      depends_on: execute/vacuum_err
136    out:
137      - log
138      - errors
139
140outputs:
141## Generated by nsaph/util/cwl_collect_outputs.py from pm25_yearly_download.cwl:
142  execute_aggregate_data:
143    type: File[]
144    outputSource: execute/aggregate_data
145  execute_data_dictionary:
146    type: File
147    outputSource: execute/data_dictionary
148  execute_consolidated_data:
149    type: File[]
150    outputSource: execute/consolidated_data
151  execute_shapes:
152    type: {'type': 'array', 'items': {'type': 'array', 'items': ['File']}}
153    outputSource: execute/shapes
154  execute_aggregate_log:
155    type: {'type': 'array', 'items': 'Any'}
156    outputSource: execute/aggregate_log
157  execute_aggregate_err:
158    type: File[]
159    outputSource: execute/aggregate_err
160  execute_ingest_log:
161    type: File
162    outputSource: execute/ingest_log
163  execute_index_log:
164    type: File
165    outputSource: execute/index_log
166  execute_vacuum_log:
167    type: File
168    outputSource: execute/vacuum_log
169  execute_ingest_err:
170    type: File
171    outputSource: execute/ingest_err
172  execute_index_err:
173    type: File
174    outputSource: execute/index_err
175  execute_vacuum_err:
176    type: File
177    outputSource: execute/vacuum_err
178## Generated by nsaph/util/cwl_collect_outputs.py from run_test.cwl:
179  verify_log:
180    type: File
181    outputSource: verify/log
182  verify_errors:
183    type: File
184    outputSource: verify/errors