ena-upload-cli 0.8.0__tar.gz → 0.9.0__tar.gz

{ena_upload_cli-0.8.0/ena_upload_cli.egg-info → ena_upload_cli-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: ena-upload-cli
-Version: 0.8.0
+Version: 0.9.0
 Summary: Command Line Interface to upload data to the European Nucleotide Archive
 Home-page: https://github.com/usegalaxy-eu/ena-upload-cli
 Author: Dilmurat Yusuf
@@ -27,6 +27,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
@@ -161,6 +162,12 @@ Please check out the [template](https://github.com/ELIXIR-Belgium/ENA-metadata-t
 #### Read info run attributes
 
 Using `read_type`	and `read_label` as header in the columns of ENA run objects will allow you to set information about reads. Values are listed in a comma separated way, without spaces. `read_type` has a controlled vocabulary, which can be found in the [ENA Documentation](https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#json-manifest-file-format). An example tsv file using these attributes can be found in [example_tables/ENA_template_runs_read_info.tsv](/example_tables/ENA_template_runs_read_info.tsv). The same syntax is also applicable for xlsx input files.
+This feature is currently limited to FastQ files.
+
+#### Encrypted files
+
+When transferring encrypted files, an additional `unencrypted_checksum` column can be added in the run table. This column should contain the md5 checksum of the unencrypted file, and note that no check is performed on this value.
+This feature is currently limited to FastQ files.
 
 #### Study and experiment custom attributes
 

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0}/README.md

@@ -128,6 +128,12 @@ Please check out the [template](https://github.com/ELIXIR-Belgium/ENA-metadata-t
 #### Read info run attributes
 
 Using `read_type`	and `read_label` as header in the columns of ENA run objects will allow you to set information about reads. Values are listed in a comma separated way, without spaces. `read_type` has a controlled vocabulary, which can be found in the [ENA Documentation](https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#json-manifest-file-format). An example tsv file using these attributes can be found in [example_tables/ENA_template_runs_read_info.tsv](/example_tables/ENA_template_runs_read_info.tsv). The same syntax is also applicable for xlsx input files.
+This feature is currently limited to FastQ files.
+
+#### Encrypted files
+
+When transferring encrypted files, an additional `unencrypted_checksum` column can be added in the run table. This column should contain the md5 checksum of the unencrypted file, and note that no check is performed on this value.
+This feature is currently limited to FastQ files.
 
 #### Study and experiment custom attributes
 

ena_upload_cli-0.9.0/ena_upload/_version.py

@@ -0,0 +1 @@
+__version__ = "0.9.0"

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0}/ena_upload/ena_upload.py

@@ -235,6 +235,8 @@ def generate_stream(schema, targets, Template, center, tool):
             file_attrib.append('read_type')
         if 'read_label' in targets:
             file_attrib.append('read_label')
+        if 'unencrypted_checksum' in targets:
+            file_attrib.append('unencrypted_checksum')
 
         other_attrib = ['alias', 'experiment_alias']
         # Create groups with alias as index
@@ -702,10 +704,8 @@ def process_args():
     parser = argparse.ArgumentParser(prog='ena-upoad-cli',
                                      description='''The program makes submission
                                      of data and respective metadata to European
-                                     Nucleotide Archive (ENA). The metadate
-                                     should be provided in separate tables
-                                     corresponding the ENA objects -- STUDY,
-                                     SAMPLE, EXPERIMENT and RUN.''',
+                                     Nucleotide Archive (ENA) easy. The metadata
+                                     can be provided in a xlsx spreadsheet or tsv tables.''',
                                      formatter_class=SmartFormatter)
     parser.add_argument('--version', action='version',
                         version='%(prog)s '+__version__)
@@ -1040,9 +1040,9 @@ def main():
         print("No submission will be performed, remove `--draft' argument to perform submission.")
     else:
         if dev:
-            url = 'https://wwwdev.ebi.ac.uk/ena/submit/drop-box/submit/?auth=ENA'
+            url = 'https://wwwdev.ebi.ac.uk/ena/submit/drop-box/submit/'
         else:
-            url = 'https://www.ebi.ac.uk/ena/submit/drop-box/submit/?auth=ENA'
+            url = 'https://www.ebi.ac.uk/ena/submit/drop-box/submit/'
 
         print(f'\nSubmitting XMLs to ENA server: {url}')
         receipt = send_schemas(schema_xmls, url, webin_id, password).text

ena_upload_cli-0.9.0/ena_upload/templates/ENA_template_FASTQFILE.xml

@@ -0,0 +1,37 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<?python
+import pandas as pd
+def attributetest(row, column):
+    if hasattr(row, column) and pd.notna(row[column]) and not str(row[column]).isspace():
+        return True
+?>
+<py:choose xmlns:py="http://genshi.edgewall.org/" test="" xmlns:xi="http://www.w3.org/2001/XInclude">
+<py:when test="attributetest(row, 'unencrypted_checksum')">
+    <FILE filename="${row.file_name}" filetype="fastq" checksum_method="MD5" checksum="${row.file_checksum}" unencrypted_checksum="${row.unencrypted_checksum}">
+    <py:if test="attributetest(row, 'read_label')">
+        <py:for each="rlabel in row.read_label.split(',')">
+        <READ_LABEL>${rlabel.strip()}</READ_LABEL>
+        </py:for>
+    </py:if>
+    <py:if test="attributetest(row, 'read_type')">
+        <py:for each="rtype in row.read_type.split(',')">
+        <xi:include href="ENA_template_READ_TYPE.xml" />
+        </py:for>
+    </py:if>
+    </FILE>
+</py:when>
+<py:otherwise>
+    <FILE filename="${row.file_name}" filetype="fastq" checksum_method="MD5" checksum="${row.file_checksum}">
+    <py:if test="attributetest(row, 'read_label')">
+        <py:for each="rlabel in row.read_label.split(',')">
+        <READ_LABEL>${rlabel.strip()}</READ_LABEL>
+        </py:for>
+    </py:if>
+    <py:if test="attributetest(row, 'read_type')">
+        <py:for each="rtype in row.read_type.split(',')">
+        <xi:include href="ENA_template_READ_TYPE.xml" />
+        </py:for>
+    </py:if>
+    </FILE>
+</py:otherwise>
+</py:choose>

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0}/ena_upload/templates/ENA_template_runs.xml

@@ -24,19 +24,8 @@ def mandatorytest(row, column, index):
                 <py:for each="index, row in file_groups.get_group(alias).iterrows()">
                 <py:if test="mandatorytest(row, 'file_type', index)">
                 <py:choose xmlns:py="http://genshi.edgewall.org/" test="">
-                <py:when test="row.file_type.lower().strip() == 'fastq'">
-                    <FILE filename="${row.file_name}" filetype="fastq" checksum_method="MD5" checksum="${row.file_checksum}">
-                        <py:if test="attributetest(row, 'read_label')">
-                        <py:for each="rlabel in row.read_label.split(',')">
-                        <READ_LABEL>${rlabel.strip()}</READ_LABEL>
-                        </py:for>
-                        </py:if>
-                        <py:if test="attributetest(row, 'read_type')">
-                        <py:for each="rtype in row.read_type.split(',')">
-                        <xi:include href="ENA_template_READ_TYPE.xml" />
-                        </py:for>
-                        </py:if>
-                    </FILE>
+                    <py:when test="row.file_type.lower().strip() == 'fastq'">
+                         <xi:include href="ENA_template_FASTQFILE.xml" />
                     </py:when>
                     <py:otherwise>
                         <xi:include href="ENA_template_FILE.xml" />

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0}/ena_upload/templates/SRA.experiment.xsd

@@ -92,7 +92,11 @@
           <xs:documentation> Random sequencing of a whole chromosome or other replicon isolated from a genome. </xs:documentation>
         </xs:annotation>
       </xs:enumeration>
-      <xs:enumeration value="RAD-Seq"/>
+      <xs:enumeration value="RAD-Seq">
+        <xs:annotation>
+          <xs:documentation> Restriction site associated DNA marker. </xs:documentation>
+        </xs:annotation>
+      </xs:enumeration> 
       <xs:enumeration value="CLONE">
         <xs:annotation>
           <xs:documentation> Genomic clone based (hierarchical) sequencing. </xs:documentation>
@@ -202,7 +206,11 @@
           <xs:documentation>Enrichment of a targeted subset of loci.</xs:documentation>
         </xs:annotation>
       </xs:enumeration>
-      <xs:enumeration value="Tethered Chromatin Conformation Capture"/>
+      <xs:enumeration value="Tethered Chromatin Conformation Capture">
+        <xs:annotation>
+          <xs:documentation> Tethered Chromatin Conformation Capture. </xs:documentation>
+        </xs:annotation>
+      </xs:enumeration>
       <xs:enumeration value="NOMe-Seq">
         <xs:annotation>
           <xs:documentation>Nucleosome Occupancy and Methylome sequencing.</xs:documentation>

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0/ena_upload_cli.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: ena-upload-cli
-Version: 0.8.0
+Version: 0.9.0
 Summary: Command Line Interface to upload data to the European Nucleotide Archive
 Home-page: https://github.com/usegalaxy-eu/ena-upload-cli
 Author: Dilmurat Yusuf
@@ -27,6 +27,7 @@ Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
 Dynamic: license
+Dynamic: license-file
 Dynamic: requires-dist
 Dynamic: requires-python
 Dynamic: summary
@@ -161,6 +162,12 @@ Please check out the [template](https://github.com/ELIXIR-Belgium/ENA-metadata-t
 #### Read info run attributes
 
 Using `read_type`	and `read_label` as header in the columns of ENA run objects will allow you to set information about reads. Values are listed in a comma separated way, without spaces. `read_type` has a controlled vocabulary, which can be found in the [ENA Documentation](https://ena-docs.readthedocs.io/en/latest/submit/reads/webin-cli.html#json-manifest-file-format). An example tsv file using these attributes can be found in [example_tables/ENA_template_runs_read_info.tsv](/example_tables/ENA_template_runs_read_info.tsv). The same syntax is also applicable for xlsx input files.
+This feature is currently limited to FastQ files.
+
+#### Encrypted files
+
+When transferring encrypted files, an additional `unencrypted_checksum` column can be added in the run table. This column should contain the md5 checksum of the unencrypted file, and note that no check is performed on this value.
+This feature is currently limited to FastQ files.
 
 #### Study and experiment custom attributes
 

{ena_upload_cli-0.8.0 → ena_upload_cli-0.9.0}/ena_upload_cli.egg-info/SOURCES.txt

@@ -38,6 +38,7 @@ ena_upload/json_parsing/json_schemas/sample_schema.json
 ena_upload/json_parsing/json_schemas/source_schema.json
 ena_upload/json_parsing/json_schemas/study_schema.json
 ena_upload/templates/ENA.project.xsd
+ena_upload/templates/ENA_template_FASTQFILE.xml
 ena_upload/templates/ENA_template_FILE.xml
 ena_upload/templates/ENA_template_LIBRARY_SELECTION.xml
 ena_upload/templates/ENA_template_LIBRARY_SOURCE.xml

ena_upload_cli-0.9.0/requirements.txt

@@ -0,0 +1,8 @@
+genshi==0.7.*
+lxml==5.3.0
+pandas>=2.0.3 , <= 3.0.0
+pyyaml==6.0.*
+requests>=2.31.0 , <= 3.0.0
+openpyxl>=3.1.2 , <= 4.0.0
+jsonschema>=4.19.1
+pytest==7.4.*

ena_upload_cli-0.8.0/ena_upload/_version.py

@@ -1 +0,0 @@
-__version__ = "0.8.0"

ena_upload_cli-0.8.0/requirements.txt

@@ -1,9 +0,0 @@
-genshi==0.7.*
-lxml==5.3.0
-pandas>=2.0.3 , <= 3.0.0
-# pyyaml set to v5.3.* to prevent problems with setuptools upon installation, as described here: https://github.com/yaml/pyyaml/issues/723#issuecomment-1638560401
-pyyaml==6.0.*
-requests>=2.31.0 , <= 3.0.0
-openpyxl>=3.1.2 , <= 4.0.0
-jsonschema>=4.19.1
-pytest==7.4.*