Delete unsentenced - Public update

@resources/bash/split-to-sentences-all-tex-files.sh

@@ -4,6 +4,15 @@
 process_file() {
     input_file="$1"
     python "$script_dir/split-to-sentences.py" "$input_file"
+
+    # Compare the contents of the original file and the 'sentenced' file
+    if cmp -s "$input_file" "${input_file%.tex}-sentenced.tex"; then
+        # If the files are identical, remove the 'sentenced' file
+        rm "${input_file%.tex}-sentenced.tex"
+        echo "No changes made to file: $input_file"
+    else
+        echo "Processed file saved as: ${input_file%.tex}-sentenced.tex"
+    fi
 }
 
 # Get the directory of the Bash script
@@ -67,11 +76,10 @@ if $all_files; then
     for file in "${tex_files[@]}"; do
         echo "Processing file: $file"
         process_file "$file"
-        if $replace_original; then
+        if $replace_original && [ -f "${file%.tex}-sentenced.tex" ]; then
             mv "$file" "${file%.tex}-unsentenced.tex"
             mv "${file%.tex}-sentenced.tex" "$file"
         fi
-        echo "Processed file saved as: ${file%.tex}-sentenced.tex"
         echo "------------------------"
     done
     echo "All .tex files in the directory have been processed."
@@ -92,9 +100,8 @@ else
     # Process the specified file
     echo "Processing file: $filename"
     process_file "$filename"
-    if $replace_original; then
+    if $replace_original && [ -f "${filename%.tex}-sentenced.tex" ]; then
         mv "$filename" "${filename%.tex}-unsentenced.tex"
         mv "${filename%.tex}-sentenced.tex" "$filename"
     fi
-    echo "Processed file saved as: ${filename%.tex}-sentenced.tex"
 fi

@resources/bash/split-to-sentences.py

@@ -1,5 +1,9 @@
+# see Claude prompt "Sentence" for development
 # 20241002:
 # - add '.} ' and '.) ' as sentencers
+# 20241006:
+# - remove bad sentence_patterns
+
 import re
 import sys
 import os
@@ -31,8 +35,6 @@ def add_newlines(text):
         placeholder_line = re.sub(pattern, '__PLACEHOLDER__', line)
 
         # Regular expression pattern to match sentence endings
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.)\s+'
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.}\s)\s+' # add '.} ' 
         sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.\)\s|\.}\s)\s+' # add '.) '
 
         # Replace sentence endings with newline character only if there is further non-whitespace material on the line

@resources/shell/split-to-sentences-all-tex-files.sh

@@ -4,6 +4,15 @@
 process_file() {
     input_file="$1"
     python "$script_dir/split-to-sentences.py" "$input_file"
+
+    # Compare the contents of the original file and the 'sentenced' file
+    if cmp -s "$input_file" "${input_file%.tex}-sentenced.tex"; then
+        # If the files are identical, remove the 'sentenced' file
+        rm "${input_file%.tex}-sentenced.tex"
+        echo "No changes made to file: $input_file"
+    else
+        echo "Processed file saved as: ${input_file%.tex}-sentenced.tex"
+    fi
 }
 
 # Get the directory of the Bash script
@@ -67,11 +76,10 @@ if $all_files; then
     for file in "${tex_files[@]}"; do
         echo "Processing file: $file"
         process_file "$file"
-        if $replace_original; then
+        if $replace_original && [ -f "${file%.tex}-sentenced.tex" ]; then
             mv "$file" "${file%.tex}-unsentenced.tex"
             mv "${file%.tex}-sentenced.tex" "$file"
         fi
-        echo "Processed file saved as: ${file%.tex}-sentenced.tex"
         echo "------------------------"
     done
     echo "All .tex files in the directory have been processed."
@@ -92,9 +100,8 @@ else
     # Process the specified file
     echo "Processing file: $filename"
     process_file "$filename"
-    if $replace_original; then
+    if $replace_original && [ -f "${filename%.tex}-sentenced.tex" ]; then
         mv "$filename" "${filename%.tex}-unsentenced.tex"
         mv "${filename%.tex}-sentenced.tex" "$filename"
     fi
-    echo "Processed file saved as: ${filename%.tex}-sentenced.tex"
 fi

@resources/shell/split-to-sentences.py

@@ -1,5 +1,9 @@
+# see Claude prompt "Sentence" for development
 # 20241002:
 # - add '.} ' and '.) ' as sentencers
+# 20241006:
+# - remove bad sentence_patterns
+
 import re
 import sys
 import os
@@ -31,8 +35,6 @@ def add_newlines(text):
         placeholder_line = re.sub(pattern, '__PLACEHOLDER__', line)
 
         # Regular expression pattern to match sentence endings
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.)\s+'
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.}\s)\s+' # add '.} ' 
         sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.\)\s|\.}\s)\s+' # add '.) '
 
         # Replace sentence endings with newline character only if there is further non-whitespace material on the line

@resources/texlive/texmf-local/tex/latex/unicode-subs-declare.sty

@@ -0,0 +1,17 @@
+% If you encounter the unicode character, substitute the LaTeX on compile
+\DeclareUnicodeCharacter{1D53C}{\mathbb{E}}  % 𝔼
+\DeclareUnicodeCharacter{1D41A}{\mathbf{a}}  % 𝐚
+\DeclareUnicodeCharacter{1D41B}{\mathbf{b}}  % 𝐛
+\DeclareUnicodeCharacter{1D41C}{\mathbf{c}}  % 𝐜
+\DeclareUnicodeCharacter{1D429}{\mathbf{p}}  % 𝐩
+\DeclareUnicodeCharacter{1D424}{\mathbf{k}}  % 𝐤
+\DeclareUnicodeCharacter{1D426}{\mathbf{m}}  % 𝐦
+\DeclareUnicodeCharacter{1D42F}{\mathbf{v}}  % 𝐯
+\DeclareUnicodeCharacter{1D432}{\mathbf{y}}  % 𝐲
+\DeclareUnicodeCharacter{1D4A2}{\mathcal{G}} % 𝒢
+\DeclareUnicodeCharacter{211B}{\mathcal{R}}  % ℛ
+\DeclareUnicodeCharacter{1D69E}{\mathrm{u}}  % 𝚞
+\DeclareUnicodeCharacter{1D69F}{\mathrm{v}}  % 𝚟
+\DeclareUnicodeCharacter{03B2}{\beta}  % β
+\DeclareUnicodeCharacter{03C3}{\sigma} % σ
+\DeclareUnicodeCharacter{03C1}{\rho} % ρ

@resources/texlive/texmf-local/tex/latex/unicode-subs-declare.tex

@@ -0,0 +1,17 @@
+% If you encounter the unicode character, substitute the LaTeX on compile
+\DeclareUnicodeCharacter{1D53C}{\mathbb{E}}  % 𝔼
+\DeclareUnicodeCharacter{1D41A}{\mathbf{a}}  % 𝐚
+\DeclareUnicodeCharacter{1D41B}{\mathbf{b}}  % 𝐛
+\DeclareUnicodeCharacter{1D41C}{\mathbf{c}}  % 𝐜
+\DeclareUnicodeCharacter{1D429}{\mathbf{p}}  % 𝐩
+\DeclareUnicodeCharacter{1D424}{\mathbf{k}}  % 𝐤
+\DeclareUnicodeCharacter{1D426}{\mathbf{m}}  % 𝐦
+\DeclareUnicodeCharacter{1D42F}{\mathbf{v}}  % 𝐯
+\DeclareUnicodeCharacter{1D432}{\mathbf{y}}  % 𝐲
+\DeclareUnicodeCharacter{1D4A2}{\mathcal{G}} % 𝒢
+\DeclareUnicodeCharacter{211B}{\mathcal{R}}  % ℛ
+\DeclareUnicodeCharacter{1D69E}{\mathrm{u}}  % 𝚞
+\DeclareUnicodeCharacter{1D69F}{\mathrm{v}}  % 𝚟
+\DeclareUnicodeCharacter{03B2}{\beta}  % β
+\DeclareUnicodeCharacter{03C3}{\sigma} % σ
+\DeclareUnicodeCharacter{03C1}{\rho} % ρ

Appendices/@resources/bash/split-to-sentences-all-tex-files.sh

@@ -4,6 +4,15 @@
 process_file() {
     input_file="$1"
     python "$script_dir/split-to-sentences.py" "$input_file"
+
+    # Compare the contents of the original file and the 'sentenced' file
+    if cmp -s "$input_file" "${input_file%.tex}-sentenced.tex"; then
+        # If the files are identical, remove the 'sentenced' file
+        rm "${input_file%.tex}-sentenced.tex"
+        echo "No changes made to file: $input_file"
+    else
+        echo "Processed file saved as: ${input_file%.tex}-sentenced.tex"
+    fi
 }
 
 # Get the directory of the Bash script
@@ -67,11 +76,10 @@ if $all_files; then
     for file in "${tex_files[@]}"; do
         echo "Processing file: $file"
         process_file "$file"
-        if $replace_original; then
+        if $replace_original && [ -f "${file%.tex}-sentenced.tex" ]; then
             mv "$file" "${file%.tex}-unsentenced.tex"
             mv "${file%.tex}-sentenced.tex" "$file"
         fi
-        echo "Processed file saved as: ${file%.tex}-sentenced.tex"
         echo "------------------------"
     done
     echo "All .tex files in the directory have been processed."
@@ -92,9 +100,8 @@ else
     # Process the specified file
     echo "Processing file: $filename"
     process_file "$filename"
-    if $replace_original; then
+    if $replace_original && [ -f "${filename%.tex}-sentenced.tex" ]; then
         mv "$filename" "${filename%.tex}-unsentenced.tex"
         mv "${filename%.tex}-sentenced.tex" "$filename"
     fi
-    echo "Processed file saved as: ${filename%.tex}-sentenced.tex"
 fi

Appendices/@resources/bash/split-to-sentences.py

@@ -1,5 +1,9 @@
+# see Claude prompt "Sentence" for development
 # 20241002:
 # - add '.} ' and '.) ' as sentencers
+# 20241006:
+# - remove bad sentence_patterns
+
 import re
 import sys
 import os
@@ -31,8 +35,6 @@ def add_newlines(text):
         placeholder_line = re.sub(pattern, '__PLACEHOLDER__', line)
 
         # Regular expression pattern to match sentence endings
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.)\s+'
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.}\s)\s+' # add '.} ' 
         sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.\)\s|\.}\s)\s+' # add '.) '
 
         # Replace sentence endings with newline character only if there is further non-whitespace material on the line

Appendices/@resources/shell/split-to-sentences-all-tex-files.sh

@@ -4,6 +4,15 @@
 process_file() {
     input_file="$1"
     python "$script_dir/split-to-sentences.py" "$input_file"
+
+    # Compare the contents of the original file and the 'sentenced' file
+    if cmp -s "$input_file" "${input_file%.tex}-sentenced.tex"; then
+        # If the files are identical, remove the 'sentenced' file
+        rm "${input_file%.tex}-sentenced.tex"
+        echo "No changes made to file: $input_file"
+    else
+        echo "Processed file saved as: ${input_file%.tex}-sentenced.tex"
+    fi
 }
 
 # Get the directory of the Bash script
@@ -67,11 +76,10 @@ if $all_files; then
     for file in "${tex_files[@]}"; do
         echo "Processing file: $file"
         process_file "$file"
-        if $replace_original; then
+        if $replace_original && [ -f "${file%.tex}-sentenced.tex" ]; then
             mv "$file" "${file%.tex}-unsentenced.tex"
             mv "${file%.tex}-sentenced.tex" "$file"
         fi
-        echo "Processed file saved as: ${file%.tex}-sentenced.tex"
         echo "------------------------"
     done
     echo "All .tex files in the directory have been processed."
@@ -92,9 +100,8 @@ else
     # Process the specified file
     echo "Processing file: $filename"
     process_file "$filename"
-    if $replace_original; then
+    if $replace_original && [ -f "${filename%.tex}-sentenced.tex" ]; then
         mv "$filename" "${filename%.tex}-unsentenced.tex"
         mv "${filename%.tex}-sentenced.tex" "$filename"
     fi
-    echo "Processed file saved as: ${filename%.tex}-sentenced.tex"
 fi

Appendices/@resources/shell/split-to-sentences.py

@@ -1,5 +1,9 @@
+# see Claude prompt "Sentence" for development
 # 20241002:
 # - add '.} ' and '.) ' as sentencers
+# 20241006:
+# - remove bad sentence_patterns
+
 import re
 import sys
 import os
@@ -31,8 +35,6 @@ def add_newlines(text):
         placeholder_line = re.sub(pattern, '__PLACEHOLDER__', line)
 
         # Regular expression pattern to match sentence endings
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.)\s+'
-        sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.}\s)\s+' # add '.} ' 
         sentence_pattern = r'(?:[.!?]|\.\'|\.\"|\$\.|\.\)\s|\.}\s)\s+' # add '.) '
 
         # Replace sentence endings with newline character only if there is further non-whitespace material on the line

Appendices/@resources/texlive/texmf-local/tex/latex/unicode-subs-declare.sty

@@ -0,0 +1,17 @@
+% If you encounter the unicode character, substitute the LaTeX on compile
+\DeclareUnicodeCharacter{1D53C}{\mathbb{E}}  % 𝔼
+\DeclareUnicodeCharacter{1D41A}{\mathbf{a}}  % 𝐚
+\DeclareUnicodeCharacter{1D41B}{\mathbf{b}}  % 𝐛
+\DeclareUnicodeCharacter{1D41C}{\mathbf{c}}  % 𝐜
+\DeclareUnicodeCharacter{1D429}{\mathbf{p}}  % 𝐩
+\DeclareUnicodeCharacter{1D424}{\mathbf{k}}  % 𝐤
+\DeclareUnicodeCharacter{1D426}{\mathbf{m}}  % 𝐦
+\DeclareUnicodeCharacter{1D42F}{\mathbf{v}}  % 𝐯
+\DeclareUnicodeCharacter{1D432}{\mathbf{y}}  % 𝐲
+\DeclareUnicodeCharacter{1D4A2}{\mathcal{G}} % 𝒢
+\DeclareUnicodeCharacter{211B}{\mathcal{R}}  % ℛ
+\DeclareUnicodeCharacter{1D69E}{\mathrm{u}}  % 𝚞
+\DeclareUnicodeCharacter{1D69F}{\mathrm{v}}  % 𝚟
+\DeclareUnicodeCharacter{03B2}{\beta}  % β
+\DeclareUnicodeCharacter{03C3}{\sigma} % σ
+\DeclareUnicodeCharacter{03C1}{\rho} % ρ

Appendices/@resources/texlive/texmf-local/tex/latex/unicode-subs-declare.tex

@@ -0,0 +1,17 @@
+% If you encounter the unicode character, substitute the LaTeX on compile
+\DeclareUnicodeCharacter{1D53C}{\mathbb{E}}  % 𝔼
+\DeclareUnicodeCharacter{1D41A}{\mathbf{a}}  % 𝐚
+\DeclareUnicodeCharacter{1D41B}{\mathbf{b}}  % 𝐛
+\DeclareUnicodeCharacter{1D41C}{\mathbf{c}}  % 𝐜
+\DeclareUnicodeCharacter{1D429}{\mathbf{p}}  % 𝐩
+\DeclareUnicodeCharacter{1D424}{\mathbf{k}}  % 𝐤
+\DeclareUnicodeCharacter{1D426}{\mathbf{m}}  % 𝐦
+\DeclareUnicodeCharacter{1D42F}{\mathbf{v}}  % 𝐯
+\DeclareUnicodeCharacter{1D432}{\mathbf{y}}  % 𝐲
+\DeclareUnicodeCharacter{1D4A2}{\mathcal{G}} % 𝒢
+\DeclareUnicodeCharacter{211B}{\mathcal{R}}  % ℛ
+\DeclareUnicodeCharacter{1D69E}{\mathrm{u}}  % 𝚞
+\DeclareUnicodeCharacter{1D69F}{\mathrm{v}}  % 𝚟
+\DeclareUnicodeCharacter{03B2}{\beta}  % β
+\DeclareUnicodeCharacter{03C3}{\sigma} % σ
+\DeclareUnicodeCharacter{03C1}{\rho} % ρ