Testing parse_theses

publications/theses.yaml

@@ -47,127 +47,85 @@
   URL: https://etda.libraries.psu.edu/paper/12437/
 - type: 'PhD Thesis'
   metadata: 'SungHoon Lee: A study of ionic materials for the energy applications through first-principles calculations and CALPHAD modeling, June 2011'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Arkapol Saengdeejing: A Computational Study of Superconducting Materials: A Case Study in Carbon-Doped MgB2, June 2011'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Guang Sheng: Phase-field simulation of phase transitions, domain stabilities and structures in ferroelectric thin films, March 2011'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Swetha Ganeshan: A first-principles study of elastic and diffusion properties of Mg based alloys, October 2010'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'James Saal: Thermodynamic Modeling of Phase Transformations: Cobalt Oxides, September 2010'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Hui Zhang: Thermodynamic Properties of Mg Based Alloys by CALPHAD Approach Couple with First-Principles: Application of Mg-Al-Ca-Ce-Si System, August 2010'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Weiming Feng: Phase-Field Models of Microstructure Evolution and New Numerical Strategies, 2009'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Manjeera Mantina, A First-Principles Methodology for Diffusion Coefficients in Metals and Dilute Alloys, 2008'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Jingxian Zhang, Phase-field simulations of microstructures involving long-range elastic, magnetostatic and electrostatic interactions, 2007'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Dongwon Shin, Thermodynamic properties of solid solutions from special quasirandom structures and CALPHAD modeling: Application to Al-Cu-Mg-Si and Hf-Si-O, 2006'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Soon Il Lee, Defect-phase equilibrium and ferroelectric phase transition behavior in non-stoichiometric BaTiO3 under various equilibrium conditions, 2006'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Tao Wang, An integrated approach for microstructure simulation: application to Ni-Al-Mo alloys, 2006'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Shengjun Zhang, Thermodynamic Investigation of the Effect of Alkali Metal Impurities on the Processing of Al and Mg Alloys, 2006.'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Yu Zhong, Investigation in Mg-Al-Ca-Sr-Zn System by computational thermodynamics approach coupled with first-principles energetics and experiments, 2005.'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'William J. Golumbfskie, Modeling of the A1-rich region of the A1-Co-Ni-Y system via computational and experimental methods for the development of high temperature A1-based alloys, 2005'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Chao Jiang, Theoretical studies of aluminum and aluminide alloys using calphad and first-principles approach, 2004'
-  URL: 
 - type: 'PhD Thesis'
   metadata: 'Koray Ozturk, Investigation in Mg-Al-Ca-Sr system by computational thermodynamics approach coupled with first-principles engergetics and experiments, 2003'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Ross, Austin: Solubility of Oxygen and Hydrogen and Diffusivity of Oxygen in the fcc Phase of the Al-fe-ni-h-o System with Application to the Formation of a Protective α-al2o3 Scale at High Temperatures. July 2015.'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Wang, Yi: Structure evolution, diffusivity and viscosity of binary al-based and ni-based metal melts: ab initio molecular dynamics study. October 2012.'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Zhang, Lei: Thermodynamic investigation of transition metal oxides via CALPHAD and first-principles methods. June 2013'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Yan (Annabelle) Ling, First-principles calculations and thermodynamic modeling of the Hf-Re binary system with extension to the Hf-Ni-Re ternary system, 2011'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Bradley Hasek, Thermodynamic modeling and first-principles calculations of the Cr-Hf-Y ternary system, 2010'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'James E. Saal, Thermodynamic modeling of the reactive sintering of Nd:YAG, 2007'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Mei Yang, Thermodynamic modeling of La1-xSrxCoO3, 2006'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'William J. Golumbfskie, Fracture toughness of spray formed Al-Y-Ni-Co alloys, 2002.'
-  URL: 
 - type: 'MS Thesis'
   metadata: 'Carl Owen Brubaker, Computational and experimental investigations of phase equilibria in magnesium alloy systems, 2002'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Frank P. McGrogan, Thermodynamic modeling of LixMn2O4 spinel for Li-ion battery cathode applications, 2013'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Yan (Annabelle) Ling, First-principles calculations and thermodynamic modeling of the Hf-Re binary system with extension to the Hf-Ni-Re ternary system, 2011'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Abdelaziz M. Elmadani, Effect of Lead Oxide Vapor on the Strength of Alumina, 2010'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Bradley Hasek, Thermodynamic modeling and first-principles calculations of the Cr-Hf-Y ternary system, 2010'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Laura Jean Lucca, An Experimental Investigation of the Mg-Al Binary System, 2010'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Justin T. Savrock, Computational Modeling of the Ce-Sn Binary System Using Thermo-Calc, 2010'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Chad M. L. Althouse, CALPHAD modeling of BaTi2O5, BaTi5O11, and Ba1.054 Ti0.946O2.946 in the BaO-TiO2 system, 2007'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Tuan Tran, Computational modeling of the Sr-Si binary system by using thermo-calc, 2006'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Matt Benzio, Phase stability in the Al-Mg binary system, 2004'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Justin Hyska, Computational modeling of the B-Ba, B-Ca, and B-Sr systems using thermo-calc, 2004'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Joseph Harvey, The verification of Dictra modeled liquation in Al-3Cu, 2003'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Jason Arndt, Computational modeling of the K-Na and F-Na binary systems using thermo-calc, 2002'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Roger Ice, Computational modeling of the Na-F and K-F binary systems using thermo-calc, 2002'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Briama Cooper, Computer simulation of liquation in Al-Cu, 2001'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Melissa Marshall, A computational thermodynamic analysis of atmospheric magnesium production, Honor, 2000'
-  URL: 
 - type: 'BS Thesis'
   metadata: 'Ricki Stevenson, Grain Size and its Effect on the Formation of Continuous Versus Discontinuous Precipitation, 2000'
-  URL: 

yaml2md.py

@@ -38,6 +38,130 @@ def parse_pressprints(header, file):
 
     return parsed_entries
 
+
+def parse_articles(header, file):
+
+    # Read the entries from the YAML file
+    with open('publications/' + file, 'r', encoding='utf-8') as f:
+        entries = yaml.safe_load(f)
+
+    # Count how many entries contain 'bumpyear' as a key in 'entries'
+    bumpyears = sum(1 for item in entries if 'bumpyear' in item) + 1
+
+    # Split 'entries' into lists at the position where a 'bumpyear' key appears
+    split_entries = []
+    temp_list = []
+    for item in entries:
+        if 'bumpyear' in item:
+            if temp_list:
+                split_entries.append(temp_list)
+            temp_list = [item]
+        else:
+            temp_list.append(item)
+    if temp_list:
+        split_entries.append(temp_list)
+
+    # Create a dictionary with 'bumpyears' items
+    bumpyear_dict = {1987 + bumpyears - i: split_entries[i] for i in range(bumpyears)}
+
+    # Remove entries containing 'bumpyear' as a key from the sublists in 'bumpyear_dict'
+    for year, sublist in bumpyear_dict.items():
+        bumpyear_dict[year] = [item for item in sublist if 'bumpyear' not in item]
+
+    parsed_entries += f"# {header}\n---\n## {max(bumpyear_dict)//10*10}'s\n\n"
+
+    # Create a string to store the formatted entries
+    id  = len(entries) - bumpyears + 1
+    for key, value in bumpyear_dict.items():
+        if key%10 == 9 and key != max(bumpyear_dict):
+            parsed_entries += f"## {key//10*10}'s\n\n"
+
+        parsed_entries += f"### {key} ({id} - {id-len(value)+1})\n\n"
+        for i, entry in enumerate(value):
+            if "ID_deprecated" in entry and entry["ID_deprecated"] != None:
+                id = int(entry["ID_deprecated"])
+
+            entryString = f"<div id='{id}'></div> **{id}.** {entry['authors']}, _{entry['title']}_, {entry['metadata']}\n\n"
+            URLs = []
+            try:
+                url = entry['DOI']
+                URLs.append(f"DOI: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+            except Exception as e:
+                if entry['DOI']:
+                    URLs.append(f"DOI: [{url}]({url})")
+            try:
+                url = entry['arXiv']
+                URLs.append(f"arXiv: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+            except Exception as e:
+                if entry['arXiv']:
+                    URLs.append(f"arXiv: [{url}]({url})")
+            try:
+                url = entry['URL']
+                URLs.append(f"URL: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+            except Exception as e:
+                if entry['URL']:
+                    URLs.append(f"URL: [{url}]({url})")
+
+            try:
+                bibentry = cn.content_negotiation(ids = entry['DOI'], format = "bibentry")
+                entryString += f"<button onclick='copyToClipboard(\"bib{id}\")'><i class='fas fa-copy'></i></button>\n" + " \| ".join(URLs) + f"\n<p id='bib{id}' style='display: none;'>{bibentry}</p>\n\n"
+            except Exception as e:
+                entryString += " \| ".join(URLs) + "\n\n"
+                print(f"An error occurred while processing the BIBENTRY DOI {entry['DOI']}: {e}")
+
+            try:
+                result = cr.works(ids = entry['DOI'])
+                if 'abstract' in result['message']:
+                    abstract = result['message']['abstract'].replace('<jats:p>', '').replace('</jats:p>', '').replace('<jats:title>Abstract</jats:title>', '')
+                    entryString += f"\n<details style='margin-bottom: 20px;'>\n  <summary>Abstract:</summary>\n  \n  {abstract}\n</details>"
+            except Exception as e:
+                print(f"An error occurred while processing the ABSTRACT of DOI {entry['DOI']}: {e}")
+
+            parsed_entries += entryString + "\n\n"
+            id -= 1
+
+    return parsed_entries
+
+
+def parse_theses(header, file):
+    parsed_entries = f"# {header}\n---\n"
+
+    # Read the entries from the YAML file
+    with open('publications/' + file, 'r', encoding='utf-8') as f:
+        entries = yaml.safe_load(f)
+
+    for type in ['PhD Thesis','MS Thesis','BS Thesis']:
+        formatted_entries += f"## {type.upper()}\n\n"
+        No = len([entry for entry in entries if entry['type'] == type])
+        for entry in entries:
+            if entry['type'] == type:
+                entryString = f"**{No}\.** {entry['metadata']}\n\n"
+                URLs = []
+                try:
+                    url = entry['URL']
+                    URLs.append(f"URL: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+                except Exception as e:
+                    if entry['URL']:
+                        URLs.append(f"URL: [{url}]({url})")
+                try:
+                    url = entry['arXiv']
+                    URLs.append(f"arXiv: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+                except Exception as e:
+                    if entry['arXiv']:
+                        URLs.append(f"arXiv: [{url}]({url})")
+                try:
+                    url = entry['Recording']
+                    URLs.append(f"Recording: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
+                except Exception as e:
+                    if entry['Recording']:
+                        URLs.append(f"Recording: [{url}]({url})")
+                entryString += " \| ".join(URLs) + "\n\n"
+                parsed_entries += entryString
+                No -= 1
+
+    return parsed_entries
+
+
 def parse_others(header, file):
     parsed_entries = f"# {header}\n---\n"
 
@@ -73,84 +197,7 @@ def parse_others(header, file):
 
 formatted_entries += parse_pressprints('IN-PRESS', 'inpress.yaml')
 
-# Read the entries from the YAML file
-with open('publications/articles.yaml', 'r', encoding='utf-8') as f:
-    entries = yaml.safe_load(f)
-
-# Count how many entries contain 'bumpyear' as a key in 'entries'
-bumpyears = sum(1 for item in entries if 'bumpyear' in item) + 1
-
-# Split 'entries' into lists at the position where a 'bumpyear' key appears
-split_entries = []
-temp_list = []
-for item in entries:
-    if 'bumpyear' in item:
-        if temp_list:
-            split_entries.append(temp_list)
-        temp_list = [item]
-    else:
-        temp_list.append(item)
-if temp_list:
-    split_entries.append(temp_list)
-
-# Create a dictionary with 'bumpyears' items
-bumpyear_dict = {1987 + bumpyears - i: split_entries[i] for i in range(bumpyears)}
-
-# Remove entries containing 'bumpyear' as a key from the sublists in 'bumpyear_dict'
-for year, sublist in bumpyear_dict.items():
-    bumpyear_dict[year] = [item for item in sublist if 'bumpyear' not in item]
-
-formatted_entries += f"# ARTICLES\n---\n## {max(bumpyear_dict)//10*10}'s\n\n"
-
-# Create a string to store the formatted entries
-id  = len(entries) - bumpyears + 1
-for key, value in bumpyear_dict.items():
-    if key%10 == 9 and key != max(bumpyear_dict):
-        formatted_entries += f"## {key//10*10}'s\n\n"
-
-    formatted_entries += f"### {key} ({id} - {id-len(value)+1})\n\n"
-    for i, entry in enumerate(value):
-        if "ID_deprecated" in entry and entry["ID_deprecated"] != None:
-            id = int(entry["ID_deprecated"])
-
-        entryString = f"<div id='{id}'></div> **{id}.** {entry['authors']}, _{entry['title']}_, {entry['metadata']}\n\n"
-        URLs = []
-        try:
-            url = entry['DOI']
-            URLs.append(f"DOI: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
-        except Exception as e:
-            if entry['DOI']:
-                URLs.append(f"DOI: [{url}]({url})")
-        try:
-            url = entry['arXiv']
-            URLs.append(f"arXiv: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
-        except Exception as e:
-            if entry['arXiv']:
-                URLs.append(f"arXiv: [{url}]({url})")
-        try:
-            url = entry['URL']
-            URLs.append(f"URL: [{re.search(r'https?://([^/]+/)?(.+)', url).group(2)}]({url})")
-        except Exception as e:
-            if entry['URL']:
-                URLs.append(f"URL: [{url}]({url})")
-
-        try:
-            bibentry = cn.content_negotiation(ids = entry['DOI'], format = "bibentry")
-            entryString += f"<button onclick='copyToClipboard(\"bib{id}\")'><i class='fas fa-copy'></i></button>\n" + " \| ".join(URLs) + f"\n<p id='bib{id}' style='display: none;'>{bibentry}</p>\n\n"
-        except Exception as e:
-            entryString += " \| ".join(URLs) + "\n\n"
-            print(f"An error occurred while processing the BIBENTRY DOI {entry['DOI']}: {e}")
-
-        try:
-            result = cr.works(ids = entry['DOI'])
-            if 'abstract' in result['message']:
-                abstract = result['message']['abstract'].replace('<jats:p>', '').replace('</jats:p>', '').replace('<jats:title>Abstract</jats:title>', '')
-                entryString += f"\n<details style='margin-bottom: 20px;'>\n  <summary>Abstract:</summary>\n  \n  {abstract}\n</details>"
-        except Exception as e:
-            print(f"An error occurred while processing the ABSTRACT of DOI {entry['DOI']}: {e}")
-
-        formatted_entries += entryString + "\n\n"
-        id -= 1
+formatted_entries += parse_articles('ARTICLES', 'articles.yaml')
 
 formatted_entries += parse_others('CONFERENCE PROCEEDINGS AND REPORTS','proceedingsandreports.yaml')
 
@@ -160,22 +207,7 @@ def parse_others(header, file):
 
 formatted_entries += parse_others('WEBCASTS', 'webcasts.yaml')
 
-formatted_entries += "# THESES\n---\n"
-
-# Read the entries from the YAML file
-with open('publications/theses.yaml', 'r', encoding='utf-8') as f:
-    entries = yaml.safe_load(f)
-
-for type in ['PhD Thesis','MS Thesis','BS Thesis']:
-    formatted_entries += f"## {type.upper()}\n\n"
-    No = len([entry for entry in entries if entry['type'] == type])
-    for entry in entries:
-        if entry['type'] == type:
-            if 'URL' in entry:
-                formatted_entries += f"**{No}\.** [{entry['metadata']}]({entry['URL']})\n\n"
-            else:
-                formatted_entries += f"**{No}\.** {entry['metadata']}\n\n"
-            No -= 1
+formatted_entries += parse_theses('THESES', 'theses.yaml')
 
 # Write the formatted entries to a .md file
 with open('index.md', 'w', encoding='utf-8') as f: