Merge pull request #87 from digital-science:v1.4

vV1.4
digital-science · Dec 30, 2024 · 9280a27 · 9280a27
2 parents a18836f + 728b163
commit 9280a27
Show file tree

Hide file tree

Showing 5 changed files with 65 additions and 24 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,12 +1,17 @@
 # Changelog
 
+## v 1.4
+
+* Fix CLI [history bug](https://github.com/digital-science/dimcli/issues/80)
+* Added DSL grammar for DSL [V2.10](https://docs.dimensions.ai/dsl/releasenotes.html#version-2-10-0-2024-april-week-of-29th)
+
 ## v 1.3
 
 * Function `extract_affiliations` return an extra column for unstructured data, with the input string.
 
 ## v 1.2
 
-* Added DSL grammar for DSL V2.8
+* Added DSL grammar for DSL [V2.8](https://docs.dimensions.ai/dsl/releasenotes.html#version-2-8-0-2023-september-week-of-25th)
 * New utility function: [utils.explode_nested_repeated_field](https://digital-science.github.io/dimcli/modules.html#dimcli.utils.misc_utils.explode_nested_repeated_field)
 
 ## v 1.1
@@ -29,7 +34,7 @@
 ## v 0.9.9
 
 * New parameters for [DslDataset.as_dataframe()](https://digital-science.github.io/dimcli/modules.html#dimcli.core.api.DslDataset.as_dataframe)  
-* Improvements to the  `--nice` and `--links` rendering of dataframes with Dimesions data
+* Improvements to the  `--nice` and `--links` rendering of dataframes with Dimensions data
   - with hyperlinks, drop IDs if title is present
   - affiliations as a list with GRID links
   - generic 'default_transform' method for extra column not in transformations

diff --git a/dimcli/VERSION.py b/dimcli/VERSION.py
@@ -1,7 +1,7 @@
 # !/usr/bin/env python
 #  -*- coding: UTF-8 -*-
 
-__version__ = "1.3"  # LATEST? =>  https://pypi.org/project/dimcli/
+__version__ = "1.4"  # LATEST? =>  https://pypi.org/project/dimcli/
 __copyright__ = "CopyRight (C) 2018-2024 by Digital Science"
 __license__ = "MIT"
 __author__ = "Michele Pasin"

diff --git a/dimcli/core/dsl_grammar_core.py b/dimcli/core/dsl_grammar_core.py
@@ -577,11 +577,11 @@
             "fieldsets": ["basics", "extras", "categories", "studies"],
             "metrics": {"count": {"description": "Total count", "name": "count"}},
             "search_fields": [
-                "title_only",
-                "raw_affiliations",
                 "full_data",
+                "title_only",
                 "investigators",
                 "title_abstract_only",
+                "raw_affiliations",
             ],
         },
         "datasets": {
@@ -875,7 +875,7 @@
                     "type": "string",
                 },
                 "repository": {
-                    "description": "Repository associtated with the dataset.",
+                    "description": "Repository associated with the dataset.",
                     "is_entity": True,
                     "is_facet": True,
                     "is_filter": True,
@@ -958,7 +958,7 @@
             },
             "fieldsets": ["basics", "categories"],
             "metrics": {"count": {"description": "Total count", "name": "count"}},
-            "search_fields": ["full_data", "title_only", "title_abstract_only"],
+            "search_fields": ["title_abstract_only", "title_only", "full_data"],
         },
         "funder_groups": {
             "fields": {
@@ -1005,6 +1005,15 @@
                     "long_description": None,
                     "type": "string",
                 },
+                "active_status": {
+                    "description": None,
+                    "is_entity": False,
+                    "is_facet": True,
+                    "is_filter": True,
+                    "is_multivalue": False,
+                    "long_description": None,
+                    "type": "string",
+                },
                 "active_year": {
                     "description": "List of active years for a grant.",
                     "is_entity": False,
@@ -1428,6 +1437,15 @@
                     "long_description": None,
                     "type": "states",
                 },
+                "research_org_types": {
+                    "description": "Type of organisation to which investigators are affiliated. This field only contains information for organisations with GRID IDs.",
+                    "is_entity": False,
+                    "is_facet": True,
+                    "is_filter": True,
+                    "is_multivalue": False,
+                    "long_description": None,
+                    "type": "string",
+                },
                 "research_orgs": {
                     "description": "GRID organisations receiving the grant (note: identifiers are automatically extracted from the source text and can be missing in some cases).",
                     "is_entity": True,
@@ -1493,11 +1511,11 @@
             },
             "search_fields": [
                 "concepts",
-                "title_only",
-                "raw_affiliations",
                 "full_data",
+                "title_only",
                 "investigators",
                 "title_abstract_only",
+                "raw_affiliations",
             ],
         },
         "organizations": {
@@ -2207,7 +2225,7 @@
                     "is_entity": False,
                     "is_facet": False,
                     "is_filter": True,
-                    "is_multivalue": False,
+                    "is_multivalue": True,
                     "long_description": None,
                     "type": "json",
                 },
@@ -2344,8 +2362,8 @@
                 "inventors",
                 "title_only",
                 "assignees",
-                "full_data",
                 "title_abstract_only",
+                "full_data",
             ],
         },
         "policy_documents": {
@@ -2551,7 +2569,7 @@
             },
             "fieldsets": ["basics", "categories"],
             "metrics": {"count": {"description": "Total count", "name": "count"}},
-            "search_fields": ["full_data", "title_only"],
+            "search_fields": ["title_only", "full_data"],
         },
         "publications": {
             "fields": {
@@ -2816,6 +2834,15 @@
                     "long_description": None,
                     "type": "string",
                 },
+                "document_type": {
+                    "description": "Document type prediction based on the content and metadata of a publication.",
+                    "is_entity": False,
+                    "is_facet": True,
+                    "is_filter": True,
+                    "is_multivalue": False,
+                    "long_description": None,
+                    "type": "string",
+                },
                 "doi": {
                     "description": "Digital object identifier.",
                     "is_entity": False,
@@ -3095,6 +3122,15 @@
                     "long_description": None,
                     "type": "string",
                 },
+                "research_org_types": {
+                    "description": "Types of organisation associated with the publication. This field only contains information for organisations with GRID IDs.",
+                    "is_entity": False,
+                    "is_facet": True,
+                    "is_filter": True,
+                    "is_multivalue": True,
+                    "long_description": None,
+                    "type": "string",
+                },
                 "research_orgs": {
                     "description": "GRID organisations associated to a publication. Identifiers are automatically extracted from author affiliations text, so they can be missing in some cases (note: this field supports :ref:`filter-functions`: ``count``).",
                     "is_entity": True,
@@ -3242,14 +3278,14 @@
             },
             "search_fields": [
                 "acknowledgements",
-                "authors",
                 "concepts",
                 "full_data_exact",
-                "full_data",
                 "terms",
                 "title_abstract_only",
                 "raw_affiliations",
+                "authors",
                 "title_only",
+                "full_data",
             ],
         },
         "reports": {
@@ -3617,7 +3653,7 @@
             },
             "fieldsets": ["basics", "categories"],
             "metrics": {"count": {"description": "Total count", "name": "count"}},
-            "search_fields": ["full_data", "concepts", "title_abstract_only"],
+            "search_fields": ["concepts", "title_abstract_only", "full_data"],
         },
         "research_org_groups": {
             "fields": {

diff --git a/dimcli/repl/history.py b/dimcli/repl/history.py
@@ -24,11 +24,10 @@ def __init__(self, filename):
         # print("HISTORY: ", filename)
         super(SelectiveFileHistory, self).__init__(filename)
 
-    def append_string(self, string):
-        " Add string to the history only if it is a valid DSL query"
+    def append_string(self, string: str) -> None:
+        "DIMCLI override: add string to the history only if it is a valid DSL query"
         l = G.allowed_starts_dsl_query()
-        for x in l:
-            if string.startswith(x):
-                self._loaded_strings.append(string)
-                self.store_string(string)
-                return
+        if string.startswith(tuple(l)):
+            self._loaded_strings.insert(0, string)
+            self.store_string(string)
+
diff --git a/dimcli/repl/repl.py b/dimcli/repl/repl.py
@@ -56,7 +56,7 @@
 >>> .export_as_html: save results from last query as HTML file. 
 >>> .export_as_bar_chart: save results from last query as Plotly bar chart. 
 >>> .export_as_jupyter: save results from last query as Jupyter notebook. 
->>> .export_as_gsheets: save results from last query as Google Sheets (requires gpread credentials). 
+>>> .export_as_gsheets: save results from last query as Google Sheets (requires gspread credentials). 
 >>> .show [optional: N]: print N results from last query, trying to build URLs for objects. Default N=10.
 >>> .json_compact: print results of last query as single-line JSON. 
 >>> .json_full: print results of last query as formatted JSON.
@@ -303,7 +303,8 @@ def run(instance="live"):
     click.secho(f"Using endpoint: {CLIENT._url} - DSL version: {_info}", dim=True)
 
     # history
-    session = PromptSession(history=SelectiveFileHistory(USER_HISTORY_FILE))
+    session = PromptSession(history=SelectiveFileHistory(USER_HISTORY_FILE))  ### December 30, 2024 
+    # session = PromptSession()
 
     databuffer = DslResultsBuffer()