pyeasyphd 0.3.4__py3-none-any.whl → 0.3.6__py3-none-any.whl

pyeasyphd/scripts/__init__.py

@@ -2,11 +2,24 @@ __all__ = [
     "run_article_md_daily_notes",
     "run_article_tex_submit",
     "run_beamer_tex_weekly_reports",
-    "run_search_for_files",
     "run_search_for_screen",
+    "run_search_for_files",
+    "run_compare_after_search",
+    "run_generate_c_Yearly",
+    "run_generate_j_e_Weekly",
+    "run_generate_j_Weekly",
+    "run_generate_j_Monthly",
+    "run_generate_j_Yearly",
 ]
 
 from .run_article_md import run_article_md_daily_notes
 from .run_article_tex import run_article_tex_submit
 from .run_beamer_tex import run_beamer_tex_weekly_reports
-from .run_search_keywords import run_search_for_files, run_search_for_screen
+from .run_generate import (
+    run_generate_c_Yearly,
+    run_generate_j_e_Weekly,
+    run_generate_j_Monthly,
+    run_generate_j_Weekly,
+    run_generate_j_Yearly,
+)
+from .run_search import run_compare_after_search, run_search_for_files, run_search_for_screen

pyeasyphd/scripts/_base.py

@@ -0,0 +1,61 @@
+import os
+from typing import Any, Dict, List
+
+
+def expand_path(path: str) -> str:
+    """Expand user home directory and environment variables in path."""
+    return os.path.expandvars(os.path.expanduser(path))
+
+
+def build_base_options(
+    include_publisher_list: List[str],
+    include_abbr_list: List[str],
+    exclude_publisher_list: List[str],
+    exclude_abbr_list: List[str],
+    path_conferences_journals_json: str,
+) -> Dict[str, Any]:
+    """
+    Build options dictionary with common configuration.
+
+    Args:
+        include_publisher_list: List of publishers to include
+        include_abbr_list: List of conference/journal abbreviations to include
+        exclude_publisher_list: List of publishers to exclude
+        exclude_abbr_list: List of conference/journal abbreviations to exclude
+        path_conferences_journals_json: Base path for conferences/journals JSON files
+
+    Returns:
+        Dictionary containing configured options
+    """
+    return {
+        "include_publisher_list": include_publisher_list,
+        "include_abbr_list": include_abbr_list,
+        "exclude_publisher_list": exclude_publisher_list,
+        "exclude_abbr_list": exclude_abbr_list,
+        "full_json_c": os.path.join(path_conferences_journals_json, "conferences.json"),
+        "full_json_j": os.path.join(path_conferences_journals_json, "journals.json"),
+        "full_json_k": os.path.join(path_conferences_journals_json, "keywords.json"),
+    }
+
+
+def build_search_options(
+    print_on_screen: bool, search_year_list: List[str], keywords_type: str, keywords_list_list: List[List[str]]
+) -> Dict[str, Any]:
+    """
+    Build search options dictionary with common configuration.
+
+    Args:
+        print_on_screen: Whether to display results on screen
+        search_year_list: List of years to filter search results
+        keywords_type: Category name for search keywords
+        keywords_list_list: Nested list of search keywords
+
+    Returns:
+        Dictionary containing configured search options
+    """
+    return {
+        "print_on_screen": print_on_screen,
+        "search_year_list": search_year_list,
+        "keywords_dict": {keywords_type: keywords_list_list},
+        "keywords_type_list": [keywords_type],
+    }

pyeasyphd/scripts/run_generate.py

@@ -0,0 +1,219 @@
+import os
+
+from pyeasyphd.tools import PaperLinksGenerator, generate_from_bibs_and_write
+from pyeasyphd.utils.utils import is_last_week_of_month
+
+from ._base import build_base_options, expand_path
+
+
+def run_generate_j_Weekly(
+    options: dict,
+    path_weekly_docs: str,
+    keywords_category_names: list[str],
+    path_spidering_bibs: str,
+    path_conferences_journals_json: str,
+):
+    # Expand and normalize file paths
+    path_weekly_docs = expand_path(path_weekly_docs)
+
+    _, path_spidering_bibs, path_conferences_journals_json, full_json_c, full_json_j, full_json_k, options_ = (
+        run_generate_base(options, "", path_spidering_bibs, path_conferences_journals_json)
+    )
+
+    # Generate md and html files
+    for gc in ["generate_data", "combine_data"]:
+        path_storage = os.path.join(path_spidering_bibs, "spider_j")
+        output_basename = os.path.join("data", "Weekly")
+        path_output = os.path.expanduser(os.path.join(path_weekly_docs, output_basename, "Journals"))
+        # "current_issue", "current_month"
+        for flag in ["current_issue", "current_month"]:
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Journals", gc, "current_year", flag, options_
+            )
+
+    # Generate links
+    for keywords_category_name in keywords_category_names:
+        output_basename = os.path.join("data", "Weekly")
+        generator = PaperLinksGenerator(full_json_c, full_json_j, full_json_k, path_weekly_docs, keywords_category_name)
+        generator.generate_weekly_links(output_basename)
+        generator.generate_keywords_links_weekly("Journals", output_basename)
+
+
+def run_generate_j_e_Weekly(
+    options: dict,
+    path_weekly_docs: str,
+    keywords_category_names: list[str],
+    path_spidering_bibs: str,
+    path_conferences_journals_json: str,
+):
+    # Expand and normalize file paths
+    path_weekly_docs = expand_path(path_weekly_docs)
+
+    _, path_spidering_bibs, path_conferences_journals_json, full_json_c, full_json_j, full_json_k, options_ = (
+        run_generate_base(options, "", path_spidering_bibs, path_conferences_journals_json)
+    )
+    options_["early_access"] = True
+
+    # Generate md and html files
+    for gc in ["generate_data", "combine_data"]:
+        path_storage = os.path.join(path_spidering_bibs, "spider_j_e")
+        output_basename = os.path.join("data", "Weekly")
+        path_output = os.path.expanduser(os.path.join(path_weekly_docs, output_basename, "Journals_Early_Access"))
+        # "current_month"
+        for flag in ["current_month"]:
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Journals", gc, "current_year", flag, options_
+            )
+
+        # "all_years"
+        for year in ["all_years"]:
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Journals", gc, year, "all_months", options_
+            )
+
+    # Generate links
+    for keywords_category_name in keywords_category_names:
+        output_basename = os.path.join("data", "Weekly")
+        generator = PaperLinksGenerator(full_json_c, full_json_j, full_json_k, path_weekly_docs, keywords_category_name)
+        generator.generate_ieee_early_access_links(output_basename)
+        generator.generate_keywords_links_weekly("Journals", output_basename)
+
+
+def run_generate_j_Monthly(
+    options: dict,
+    path_monthly_docs: str,
+    keywords_category_names: list[str],
+    path_spidering_bibs: str,
+    path_conferences_journals_json: str,
+):
+    # Expand and normalize file paths
+    path_monthly_docs = expand_path(path_monthly_docs)
+
+    _, path_spidering_bibs, path_conferences_journals_json, full_json_c, full_json_j, full_json_k, options_ = (
+        run_generate_base(options, "", path_spidering_bibs, path_conferences_journals_json)
+    )
+
+    # Generate md and html files
+    for gc in ["generate_data", "combine_data"]:
+        path_storage = os.path.join(path_spidering_bibs, "spider_j")
+        output_basename = os.path.join("data", "Monthly")
+        path_output = os.path.expanduser(os.path.join(path_monthly_docs, output_basename, "Journals"))
+        # "all_months"
+        for flag in ["all_months"]:
+            if flag == "all_months":
+                if not is_last_week_of_month():
+                    continue
+
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Journals", gc, "current_year", flag, options_
+            )
+
+    # Generate links
+    for keywords_category_name in keywords_category_names:
+        output_basename = os.path.join("data", "Monthly")
+        generator = PaperLinksGenerator(
+            full_json_c, full_json_j, full_json_k, path_monthly_docs, keywords_category_name
+        )
+        generator.generate_monthly_links(output_basename)
+        generator.generate_keywords_links_monthly("Journals", output_basename)
+
+
+def run_generate_j_Yearly(
+    options: dict,
+    path_yearly_docs: str,
+    keywords_category_names: list[str],
+    path_spidered_bibs: str,
+    path_conferences_journals_json: str,
+    year_list: list[str],
+):
+    # Expand and normalize file paths
+    path_yearly_docs = expand_path(path_yearly_docs)
+
+    path_spidered_bibs, _, path_conferences_journals_json, full_json_c, full_json_j, full_json_k, options_ = (
+        run_generate_base(options, path_spidered_bibs, "", path_conferences_journals_json)
+    )
+
+    # Generate md and html files
+    for gc in ["generate_data", "combine_data"]:
+        path_storage = os.path.join(path_spidered_bibs, "Journals")
+        output_basename = os.path.join("data", "Yearly")
+        path_output = os.path.expanduser(os.path.join(path_yearly_docs, output_basename, "Journals"))
+        # "2024", "2023", "2022", "2021", "2020", "2019", "2018", "2017", "2016", "2015"
+        for year in year_list:
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Journals", gc, [year], "all_months", options_
+            )
+
+    # Generate links
+    for keywords_category_name in keywords_category_names:
+        output_basename = os.path.join("data", "Yearly")
+        generator = PaperLinksGenerator(full_json_c, full_json_j, full_json_k, path_yearly_docs, keywords_category_name)
+        generator.generate_yearly_links("Journals", output_basename)
+        generator.generate_keywords_links_yearly("Journals", output_basename)
+
+
+def run_generate_base(
+    options: dict, path_spidered_bibs: str, path_spidering_bibs: str, path_conferences_journals_json: str
+):
+    # Expand and normalize file paths
+    path_spidered_bibs = expand_path(path_spidered_bibs)
+    path_spidering_bibs = expand_path(path_spidering_bibs)
+    path_conferences_journals_json = expand_path(path_conferences_journals_json)
+
+    # Configure options
+    options_ = build_base_options(
+        include_publisher_list=[],
+        include_abbr_list=[],
+        exclude_publisher_list=["arXiv"],
+        exclude_abbr_list=[],
+        path_conferences_journals_json=path_conferences_journals_json,
+    )
+    options_.update(options)
+
+    full_json_c = options_["full_json_c"]
+    full_json_j = options_["full_json_j"]
+    full_json_k = options_["full_json_k"]
+
+    return (
+        path_spidered_bibs,
+        path_spidering_bibs,
+        path_conferences_journals_json,
+        full_json_c,
+        full_json_j,
+        full_json_k,
+        options_
+    )
+
+
+def run_generate_c_Yearly(
+    options: dict,
+    path_yearly_docs: str,
+    keywords_category_names: list[str],
+    path_spidered_bibs: str,
+    path_conferences_journals_json: str,
+    year_list: list[str],
+):
+    # Expand and normalize file paths
+    path_yearly_docs = expand_path(path_yearly_docs)
+
+    path_spidered_bibs, _, path_conferences_journals_json, full_json_c, full_json_j, full_json_k, options_ = (
+        run_generate_base(options, path_spidered_bibs, "", path_conferences_journals_json)
+    )
+
+    # Generate md and html files
+    for gc in ["generate_data", "combine_data"]:
+        path_storage = os.path.join(path_spidered_bibs, "Conferences")
+        output_basename = os.path.join("data", "Yearly")
+        path_output = os.path.expanduser(os.path.join(path_yearly_docs, output_basename, "Conferences"))
+        # "2025", "2024", "2023", "2022", "2021", "2020", "2019", "2018", "2017", "2016", "2015"
+        for year in year_list:
+            generate_from_bibs_and_write(
+                path_storage, path_output, output_basename, "Conferences", gc, [year], "all_months", options_
+            )
+
+    # Generate links
+    for keywords_category_name in keywords_category_names:
+        output_basename = os.path.join("data", "Yearly")
+        generator = PaperLinksGenerator(full_json_c, full_json_j, full_json_k, path_yearly_docs, keywords_category_name)
+        generator.generate_yearly_links("Conferences", output_basename)
+        generator.generate_keywords_links_yearly("Conferences", output_basename)

pyeasyphd/scripts/run_search.py

@@ -0,0 +1,213 @@
+import os
+from typing import Any, Dict, List
+
+from pyadvtools import transform_to_data_list
+from pybibtexer.tools import compare_bibs_with_zotero
+
+from pyeasyphd.tools import Searchkeywords
+
+from ._base import build_base_options, build_search_options, expand_path
+
+
+def run_search_for_screen(
+    acronym: str,
+    year: int,
+    title: str,
+    path_spidered_bibs: str,
+    path_spidering_bibs: str,
+    path_conferences_journals_json: str,
+) -> None:
+    """
+    Run search for screen display with specific conference/journal parameters.
+
+    Args:
+        acronym: Conference/journal acronym to search for
+        year: Publication year to filter by
+        title: Paper title used as search keyword
+        path_spidered_bibs: Path to spidered bibliography files
+        path_spidering_bibs: Path to spidering bibliography files
+        path_conferences_journals_json: Path to conferences/journals JSON files
+    """
+    # Expand and normalize file paths
+    path_spidered_bibs = expand_path(path_spidered_bibs)
+    path_spidering_bibs = expand_path(path_spidering_bibs)
+    path_conferences_journals_json = expand_path(path_conferences_journals_json)
+
+    # Configure search options
+    options = {
+        **build_base_options(
+            include_publisher_list=[],
+            include_abbr_list=[acronym],
+            exclude_publisher_list=["arXiv"],
+            exclude_abbr_list=[],
+            path_conferences_journals_json=path_conferences_journals_json,
+        ),
+        **build_search_options(
+            print_on_screen=True, search_year_list=[str(year)], keywords_type="Temp", keywords_list_list=[[title]]
+        ),
+    }
+
+    # Execute searches across different bibliography sources
+    _execute_searches(options, "", path_spidered_bibs, path_spidering_bibs)
+
+
+def run_search_for_files(
+    keywords_type: str,
+    keywords_list_list: List[List[str]],
+    path_main_output: str,
+    path_spidered_bibs: str,
+    path_spidering_bibs: str,
+    path_conferences_journals_json: str,
+) -> None:
+    """
+    Run search and save results to files with custom keywords.
+
+    Args:
+        keywords_type: Category name for the search keywords
+        keywords_list_list: Nested list of keywords to search for
+        path_main_output: Main output directory for search results
+        path_spidered_bibs: Path to spidered bibliography files
+        path_spidering_bibs: Path to spidering bibliography files
+        path_conferences_journals_json: Path to conferences/journals JSON files
+    """
+    # Expand and normalize file paths
+    path_main_output = expand_path(path_main_output)
+    path_spidered_bibs = expand_path(path_spidered_bibs)
+    path_spidering_bibs = expand_path(path_spidering_bibs)
+    path_conferences_journals_json = expand_path(path_conferences_journals_json)
+
+    # Configure search options
+    options = {
+        **build_base_options(
+            include_publisher_list=[],
+            include_abbr_list=[],
+            exclude_publisher_list=["arXiv"],
+            exclude_abbr_list=[],
+            path_conferences_journals_json=path_conferences_journals_json,
+        ),
+        **build_search_options(
+            print_on_screen=False,
+            search_year_list=[],
+            keywords_type=keywords_type,
+            keywords_list_list=keywords_list_list,
+        ),
+    }
+    # Execute searches across different bibliography sources
+    _execute_searches(options, path_main_output, path_spidered_bibs, path_spidering_bibs)
+
+
+def _execute_searches(
+    options: Dict[str, Any], path_main_output: str, path_spidered_bibs: str, path_spidering_bibs: str
+) -> None:
+    """
+    Execute searches across different bibliography sources.
+
+    Args:
+        options: Search configuration options
+        path_main_output: Base path for search results output
+        path_spidered_bibs: Path to spidered bibliography files
+        path_spidering_bibs: Path to spidering bibliography files
+    """
+    # Search in spidered bibliographies (Conferences and Journals)
+    for cj in ["Conferences", "Journals"]:
+        path_storage = os.path.join(path_spidered_bibs, cj)
+        path_output = os.path.join(path_main_output, "Search_spidered_bib", cj)
+        Searchkeywords(path_storage, path_output, options).run()
+
+    # Search in spidering bibliographies (Journals and Journals Early Access)
+    for je in ["spider_j", "spider_j_e"]:
+        path_storage = os.path.join(path_spidering_bibs, je)
+        path_output = os.path.join(path_main_output, "Search_spidering_bib", je)
+        Searchkeywords(path_storage, path_output, options).run()
+
+
+def run_compare_after_search(
+    zotero_bib: str, keywords_type: str, path_main_output: str, path_conferences_journals_json: str
+):
+    """
+    Compare search results with Zotero bibliography and generate comparison report.
+
+    Args:
+        zotero_bib: Path to Zotero bibliography file
+        keywords_type: Category name for the search keywords used
+        path_main_output: Main output directory for search results and comparison
+        path_conferences_journals_json: Path to conferences/journals JSON files
+    """
+    # Expand and normalize file paths
+    zotero_bib = expand_path(zotero_bib)
+    path_main_output = expand_path(path_main_output)
+    path_conferences_journals_json = expand_path(path_conferences_journals_json)
+
+    # Configure search options
+    options = {
+        **build_base_options(
+            include_publisher_list=[],
+            include_abbr_list=[],
+            exclude_publisher_list=["arXiv"],
+            exclude_abbr_list=[],
+            path_conferences_journals_json=path_conferences_journals_json,
+        ),
+        **build_search_options(
+            print_on_screen=False, search_year_list=[], keywords_type=keywords_type, keywords_list_list=[]
+        ),
+    }
+
+    # Download bibliography files from local search results
+    download_bib = _download_bib_from_local(path_main_output, keywords_type)
+
+    # Generate comparison output path and run comparison
+    path_output = os.path.join(path_main_output, "comparison_new")
+    compare_bibs_with_zotero(zotero_bib, download_bib, path_output, options)
+
+    return None
+
+
+def _generate_data_list(path_output: str, folder_name: str, keywords_type: str) -> list[str]:
+    """
+    Extract bibliography data content from files in specified folder structure.
+
+    Args:
+        path_output: Base output path for search results
+        folder_name: Specific folder name within the output structure
+        keywords_type: Category name for the search keywords used
+
+    Returns:
+        List of bibliography data content extracted from .bib files in the specified folders
+    """
+    data_list = []
+
+    # Extract data from both title and abstract bibliography folders
+    for bib_type in ["title-bib-zotero", "abstract-bib-zotero"]:
+        folder_path = os.path.join(path_output, f"{folder_name}-Separate", "article", keywords_type, bib_type)
+
+        # Extract bibliography data content if folder exists
+        if os.path.exists(folder_path):
+            data_list.extend(transform_to_data_list(folder_path, ".bib"))
+
+    return data_list
+
+
+def _download_bib_from_local(path_output: str, keywords_type: str) -> list[str]:
+    """
+    Collect bibliography data content from all local search result directories.
+
+    Args:
+        path_output: Base output path containing search results
+        keywords_type: Category name for the search keywords used
+
+    Returns:
+        Combined list of bibliography data content from all .bib files in search results
+    """
+    data_list = []
+
+    # Collect data from spidered bibliographies (Conferences and Journals)
+    for cj in ["Conferences", "Journals"]:
+        folder_name = os.path.join("Search_spidered_bib", cj)
+        data_list.extend(_generate_data_list(path_output, folder_name, keywords_type))
+
+    # Collect data from spidering bibliographies (journal sources)
+    for je in ["spider_j", "spider_j_e"]:
+        folder_name = os.path.join("Search_spidering_bib", je)
+        data_list.extend(_generate_data_list(path_output, folder_name, keywords_type))
+
+    return data_list

{pyeasyphd-0.3.4.dist-info → pyeasyphd-0.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyeasyphd
-Version: 0.3.4
+Version: 0.3.6
 Summary: pyeasyphd
 License: GPL-3.0-or-later
 License-File: LICENSE

{pyeasyphd-0.3.4.dist-info → pyeasyphd-0.3.6.dist-info}/RECORD

@@ -26,11 +26,13 @@ pyeasyphd/main/python_run_tex.py,sha256=9Syu8qRjPXN3gEabfRUWxwTFBm_izIcB4yFhsz3Q
 pyeasyphd/pyeasyphd.py,sha256=OAwbwq2rSXLSk2AoTAF8hmlOMRSRfvDn1Uqk-zkuqH8,3470
 pyeasyphd/pyeasyphd.sublime-settings,sha256=KcXx3DjyVf8UfnB4FP4u-jaTQU3Cuj24OvxGCZvXAsw,3135
 pyeasyphd/pyeasyphd.sublime-syntax,sha256=pXylbA-tye-K5dCTjEJLFVRqtY1T7AgWZ4laxo-dnaE,73
-pyeasyphd/scripts/__init__.py,sha256=R-gQqvYxkiQFZXjzxIWSNheWRolklXb1QY8b2nrKKZk,415
+pyeasyphd/scripts/__init__.py,sha256=aCI90-4ekx3y-F21BwbuaE7kUZOmxcevlvYWYsHOuiw,780
+pyeasyphd/scripts/_base.py,sha256=YY8dmqBN8mBW1Opu0A5Usd_j2RSeMIxht5kXHrQaBFo,2232
 pyeasyphd/scripts/run_article_md.py,sha256=ZjdO03YRDokSqo-Rffby-1p6_P35N4amERKHe4yS6_0,4127
 pyeasyphd/scripts/run_article_tex.py,sha256=TuTEQk7y-Ykos3a_mlEJzyFnT9RKsAYjGXnwHJa5cjY,4672
 pyeasyphd/scripts/run_beamer_tex.py,sha256=UUOadRfmyWGfK__9NzJIUo1lAiDRB5edxRsfhrS3Ejo,4209
-pyeasyphd/scripts/run_search_keywords.py,sha256=HAbELDQy2buf2pxZvmdAM6GrS8W9dGSsuf8cOB5GyFA,6178
+pyeasyphd/scripts/run_generate.py,sha256=fLUQ6yCDY_jxpOWlSusHQlZblbvbdHpkb9Bv703jTQ0,8972
+pyeasyphd/scripts/run_search.py,sha256=DPpFcctEuzHCBZQdoGsETzqtIq_dfcMfEPd5lUTNKHg,8106
 pyeasyphd/tools/__init__.py,sha256=u1MZu_JjVac3HhEmcSTwroS83UVu0W5Vspy3Wu_-GH8,496
 pyeasyphd/tools/generate/generate_from_bibs.py,sha256=Dp1MyADwIRb9qFTFOkMPJLaeeh7NBjuiSLBN7smP2eo,7640
 pyeasyphd/tools/generate/generate_html.py,sha256=JzUEqgTVCaFzd4hXTYUEf0cVSO1QRe0nVUS72W6oyyU,5349
@@ -44,7 +46,7 @@ pyeasyphd/tools/search/search_keywords.py,sha256=YCurXuoYeU1ftve0cb8Hcn_g2FXCXf7
 pyeasyphd/tools/search/search_writers.py,sha256=Dz6D8m17R7x8NT7_PCjwmzlq29AfUz-N6sjyCguDTo4,15702
 pyeasyphd/tools/search/utils.py,sha256=bo7xtIZu31dQvjol1lwyWq1t6ldbw28oondwK8VbAqk,7562
 pyeasyphd/utils/utils.py,sha256=kWxzzgNwz77K9Q7j-RKTaoPpxqiVLVtaBMMhLuEenwE,3128
-pyeasyphd-0.3.4.dist-info/METADATA,sha256=yTHmsfDu8UqmssQFuVtZhpMeEc8PI8azisZEwGHoyDU,985
-pyeasyphd-0.3.4.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-pyeasyphd-0.3.4.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-pyeasyphd-0.3.4.dist-info/RECORD,,
+pyeasyphd-0.3.6.dist-info/METADATA,sha256=sOsSH-zW116-879Yv6TRJPI0cEbM2KR0XtepSUpT-8U,985
+pyeasyphd-0.3.6.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+pyeasyphd-0.3.6.dist-info/licenses/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pyeasyphd-0.3.6.dist-info/RECORD,,

pyeasyphd/scripts/run_search_keywords.py

@@ -1,159 +0,0 @@
-import os
-from typing import Any, Dict, List
-
-from pyeasyphd.tools import Searchkeywords
-
-
-def run_search_for_screen(
-    acronym: str,
-    year: int,
-    title: str,
-    path_spidered_bibs: str,
-    path_spidering_bibs: str,
-    path_conferences_journals_json: str,
-) -> None:
-    """
-    Run search for screen display with specific conference/journal parameters.
-
-    Args:
-        acronym: Conference/journal acronym to search for
-        year: Publication year to filter by
-        title: Paper title used as search keyword
-        path_spidered_bibs: Path to spidered bibliography files
-        path_spidering_bibs: Path to spidering bibliography files
-        path_conferences_journals_json: Path to conferences/journals JSON files
-    """
-    # Expand and normalize file paths
-    path_spidered_bibs = _expand_path(path_spidered_bibs)
-    path_spidering_bibs = _expand_path(path_spidering_bibs)
-    path_conferences_journals_json = _expand_path(path_conferences_journals_json)
-
-    # Configure search options
-    options = _build_search_options(
-        print_on_screen=True,
-        search_year_list=[str(year)],
-        include_publisher_list=[],
-        include_abbr_list=[acronym],
-        exclude_publisher_list=["arXiv"],
-        exclude_abbr_list=[],
-        keywords_type="Temp",
-        keywords_list_list=[[title]],
-        path_conferences_journals_json=path_conferences_journals_json,
-    )
-
-    # Execute searches across different bibliography sources
-    _execute_searches(options, "", path_spidered_bibs, path_spidering_bibs)
-
-
-def run_search_for_files(
-    keywords_type: str,
-    keywords_list_list: List[List[str]],
-    path_main_output: str,
-    path_spidered_bibs: str,
-    path_spidering_bibs: str,
-    path_conferences_journals_json: str,
-) -> None:
-    """
-    Run search and save results to files with custom keywords.
-
-    Args:
-        keywords_type: Category name for the search keywords
-        keywords_list_list: Nested list of keywords to search for
-        path_main_output: Main output directory for search results
-        path_spidered_bibs: Path to spidered bibliography files
-        path_spidering_bibs: Path to spidering bibliography files
-        path_conferences_journals_json: Path to conferences/journals JSON files
-    """
-    # Expand and normalize file paths
-    path_main_output = _expand_path(path_main_output)
-    path_spidered_bibs = _expand_path(path_spidered_bibs)
-    path_spidering_bibs = _expand_path(path_spidering_bibs)
-    path_conferences_journals_json = _expand_path(path_conferences_journals_json)
-
-    # Configure search options
-    options = _build_search_options(
-        print_on_screen=False,
-        search_year_list=[],
-        include_publisher_list=[],
-        include_abbr_list=[],
-        exclude_publisher_list=["arXiv"],
-        exclude_abbr_list=[],
-        keywords_type=keywords_type,
-        keywords_list_list=keywords_list_list,
-        path_conferences_journals_json=path_conferences_journals_json,
-    )
-
-    # Execute searches across different bibliography sources
-    _execute_searches(options, path_main_output, path_spidered_bibs, path_spidering_bibs)
-
-
-def _expand_path(path: str) -> str:
-    """Expand user home directory and environment variables in path."""
-    return os.path.expandvars(os.path.expanduser(path))
-
-
-def _build_search_options(
-    print_on_screen: bool,
-    search_year_list: List[str],
-    include_publisher_list: List[str],
-    include_abbr_list: List[str],
-    exclude_publisher_list: List[str],
-    exclude_abbr_list: List[str],
-    keywords_type: str,
-    keywords_list_list: List[List[str]],
-    path_conferences_journals_json: str,
-) -> Dict[str, Any]:
-    """
-    Build search options dictionary with common configuration.
-
-    Args:
-        print_on_screen: Whether to display results on screen
-        search_year_list: List of years to filter search results
-        include_publisher_list: List of publishers to include
-        include_abbr_list: List of conference/journal abbreviations to include
-        exclude_publisher_list: List of publishers to exclude from search
-        exclude_abbr_list: List of conference/journal abbreviations to exclude from search
-        keywords_type: Category name for search keywords
-        keywords_list_list: Nested list of search keywords
-        path_conferences_journals_json: Base path for conferences/journals JSON files
-
-    Returns:
-        Dictionary containing configured search options
-    """
-    return {
-        "print_on_screen": print_on_screen,
-        "search_year_list": search_year_list,
-        "include_publisher_list": include_publisher_list,
-        "include_abbr_list": include_abbr_list,
-        "exclude_publisher_list": exclude_publisher_list,
-        "exclude_abbr_list": exclude_abbr_list,
-        "keywords_dict": {keywords_type: keywords_list_list},
-        "keywords_type_list": [keywords_type],
-        "full_json_c": os.path.join(path_conferences_journals_json, "conferences.json"),
-        "full_json_j": os.path.join(path_conferences_journals_json, "journals.json"),
-    }
-
-
-def _execute_searches(
-    options: Dict[str, Any], path_main_output: str, path_spidered_bibs: str, path_spidering_bibs: str
-) -> None:
-    """
-    Execute searches across different bibliography sources.
-
-    Args:
-        options: Search configuration options
-        path_main_output: Base path for search results output
-        path_spidered_bibs: Path to spidered bibliography files
-        path_spidering_bibs: Path to spidering bibliography files
-    """
-    # Search in spidered bibliographies (Conferences and Journals)
-    for cj in ["Conferences", "Journals"]:
-        path_storage = os.path.join(path_spidered_bibs, cj)
-        path_output = os.path.join(path_main_output, "Search_spidered_bib", cj)
-        Searchkeywords(path_storage, path_output, options).run()
-
-    # Search in spidering bibliographies (Journals and Journals Early Access)
-    for je in ["spider_j", "spider_j_e"]:
-        path_storage = os.path.join(path_spidering_bibs, je)
-        path_output = os.path.join(path_main_output, "Search_spidering_bib", je)
-        Searchkeywords(path_storage, path_output, options).run()