diff --git a/semester3/spca/code-examples/00_c/00_intro.c b/semester3/spca/code-examples/00_c/00_intro.c index 7635eed..341ecbb 100644 --- a/semester3/spca/code-examples/00_c/00_intro.c +++ b/semester3/spca/code-examples/00_c/00_intro.c @@ -13,4 +13,5 @@ int main( int argc, char *argv[] ) { printf( "Arg %d: %s\n", i, argv[ i ] ); // Outputs the i-th argument from CLI get_user_input_int( "Select a number" ); // Function calls as in any other language + return 0; // Return a POSIX exit code } diff --git a/semester3/spca/code-examples/00_c/01_func.c b/semester3/spca/code-examples/00_c/01_func.c index 374e138..399cbbf 100644 --- a/semester3/spca/code-examples/00_c/01_func.c +++ b/semester3/spca/code-examples/00_c/01_func.c @@ -1,9 +1,11 @@ #include "01_func.h" +#include int get_user_input_int( char prompt[] ) { int input_data; - printf( "%s", prompt ); // Always wrap strings like this for printf - scanf( "%d", &input_data ); // Get user input from CLI + printf( "%s", prompt ); // Always wrap strings like this for printf + scanf( "%d", &input_data ); // Get user input from CLI + int input_data_copy = input_data; // Value copied // If statements just like any other language if ( input_data ) @@ -11,6 +13,7 @@ int get_user_input_int( char prompt[] ) { else printf( "Input is zero" ); + // Switch statements just like in any other language switch ( input_data ) { case 5: printf( "You win!" ); @@ -21,17 +24,20 @@ int get_user_input_int( char prompt[] ) { printf( "No win" ); // Case for any not covered input } - int input_data_copy = input_data; - while ( input_data > 1 ) { input_data -= 1; printf( "Hello World\n" ); } + // Inversed while loop (executes at least once) do { input_data -= 1; printf( "Bye World\n" ); + if ( input_data_copy == 0 ) + goto this_is_a_label; } while ( input_data_copy > 1 ); +this_is_a_label: + printf( "Jumped to label" ); return 0; } diff --git a/semester3/spca/code-examples/00_c/02_declarations.c b/semester3/spca/code-examples/00_c/02_declarations.c new file mode 100644 index 0000000..add64e3 --- /dev/null +++ b/semester3/spca/code-examples/00_c/02_declarations.c @@ -0,0 +1,32 @@ +int my_int; // Allocates memory on the stack. + // Variable is global (read / writable by entire program) +static int my_local_int; // only available locally (in this file) +const int MY_CONST = 10; // constant (immutable), convention: SCREAM_CASE + +enum { ONE, TWO } num; // Enum. ONE will get value 0, TWO has value 1 + +enum { O = 2, T = 1 } n; // Enum with values specified + +// Structs are like classes, but contain no logic +struct MyStruct { + int el1; + int el2; +}; + +int fun( int j ) { + static int i = 0; // Persists across calls of fun + short my_var = 1; // Block scoped (deallocated when going out of scope) + int my_var_dbl = (int) my_var; // Explicit casting (works between almost all types) + return i; +} + +int main( int argc, char *argv[] ) { + if ( ( my_local_int = fun( 10 ) ) ) { + // Every c statement is also an expression, i.e. you can do the above! + } + struct MyStruct test; // Allocate memory on stack for struct + struct MyStruct *test_p = &test; // Pointer to memory where test resides + test.el1 = 1; // Direct element access + test_p->el2 = 2; // Via pointer + return 0; +} diff --git a/semester3/spca/code-examples/00_c/03_operators.c b/semester3/spca/code-examples/00_c/03_operators.c new file mode 100644 index 0000000..347a043 --- /dev/null +++ b/semester3/spca/code-examples/00_c/03_operators.c @@ -0,0 +1,3 @@ +int main( int argc, char *argv[] ) { + return 0; +} diff --git a/semester3/spca/code-examples/00_c/02_pointers.c b/semester3/spca/code-examples/00_c/04_pointers.c similarity index 100% rename from semester3/spca/code-examples/00_c/02_pointers.c rename to semester3/spca/code-examples/00_c/04_pointers.c diff --git a/semester3/spca/parts/00_c/00_intro.tex b/semester3/spca/parts/00_c/00_intro.tex index 2a4df05..b22f702 100644 --- a/semester3/spca/parts/00_c/00_intro.tex +++ b/semester3/spca/parts/00_c/00_intro.tex @@ -13,3 +13,5 @@ This of course leads to \texttt{C} performing excellently and there are many pro but instead optimized \texttt{C} code that is then compiled into machine code using a \texttt{C} compiler. This has a number of benefits, most notably that \texttt{C} compilers can produce very efficient assembly, as lots of effort is put into the \texttt{C} compilers by the hardware manufacturers. + +There are many great \lC\ tutorials out there, a simple one (as for many other languages too) can be found \hlhref{https://www.w3schools.com/c/index.php}{here} diff --git a/semester3/spca/parts/00_c/01_syntax.tex b/semester3/spca/parts/00_c/01_basics/00_intro.tex similarity index 73% rename from semester3/spca/parts/00_c/01_syntax.tex rename to semester3/spca/parts/00_c/01_basics/00_intro.tex index 0db7469..5d907ab 100644 --- a/semester3/spca/parts/00_c/01_syntax.tex +++ b/semester3/spca/parts/00_c/01_basics/00_intro.tex @@ -1,4 +1,4 @@ -\subsection{The Syntax} +\subsection{Basics} \texttt{C} uses a very similar syntax as many other programming languages, like \texttt{Java}, \texttt{JavaScript} and many more\dots to be precise, it is \textit{them} that use the \texttt{C} syntax, not the other way around. So: \inputcodewithfilename{c}{code-examples/00_c/}{00_intro.c} @@ -7,7 +7,6 @@ In \texttt{C} we are referring to the implementation of a function as a \bi{(fun and to the definition of the function signature (or variables, without initializing them) as the \bi{(function) declaration} (or, correspondingly, \textit{variable declaration}). \texttt{C} code is usuallt split into the source files, ending in \texttt{.c} (where the local functions and variables are declared, as well as all function definitions) -and the header files, ending in \texttt{.h}, where the external declarations are defined. Usually, no definition of functions are in the \texttt{.h} files +and the header files, ending in \texttt{.h}, usually sharing the filename of the source file, where the external declarations are defined. +By convention, no definition of functions are in the \texttt{.h} files, and neither variables, but there is nothing preventing you from putting them there. \inputcodewithfilename{c}{code-examples/00_c/}{01_func.h} - -\inputcodewithfilename{c}{code-examples/00_c/}{01_func.c} diff --git a/semester3/spca/parts/00_c/01_basics/01_control-flow.tex b/semester3/spca/parts/00_c/01_basics/01_control-flow.tex new file mode 100644 index 0000000..b95731a --- /dev/null +++ b/semester3/spca/parts/00_c/01_basics/01_control-flow.tex @@ -0,0 +1,14 @@ +\newpage +\subsubsection{Control Flow} +Many of the control-flow structures of \texttt{C} can be found in the below code snippet. +A note of caution when using goto: It is almost never a good idea (can lead to unexpected behaviour, is hard to maintain, etc). +Where it however is very handy is for error recovery (and cleanup functions) and early termination of multiple loops (jumping out of a loop). +So, for example, if you have to run multiple functions to set something up and one of them fails, +you can jump to a label and have all cleanup code execute that you have specified there. +And because the labels are (as in Assembly) simply skipped over during execution, you can make very nice cleanup code. +We can also use \texttt{continue} and \texttt{break} statements similarly to \texttt{Java}, they do not however accept labels. +(Reminder: \texttt{continue} skips the loop body and goes to the next iteration) + +\inputcodewithfilename{c}{code-examples/00_c/}{01_func.c} + + diff --git a/semester3/spca/parts/00_c/01_basics/02_declarations.tex b/semester3/spca/parts/00_c/01_basics/02_declarations.tex new file mode 100644 index 0000000..fe4c41e --- /dev/null +++ b/semester3/spca/parts/00_c/01_basics/02_declarations.tex @@ -0,0 +1,37 @@ +\newpage +\subsubsection{Declarations} +We have already seen a few examples for how \texttt{C} handles declarations. +In concept they are similar (and scoping works the same) to most other \texttt{C}-like programming languages, including \texttt{Java}. +\inputcodewithfilename{c}{code-examples/00_c/}{02_declarations.c} + +A peculiarity of \texttt{C} is that the bit-count is not defined by the language, but rather the hardware it is compiled for. +\begin{fullTable}{llll}{\texttt{C} data type & typical 32-bit & ia32 & x86-64}{Comparison of byte-sizes for each datatype on different architectures} + \texttt{char} & 1 & 1 & 1 \\ + \texttt{short} & 2 & 2 & 2 \\ + \texttt{int} & 4 & 4 & 4 \\ + \texttt{long} & 4 & 4 & 8 \\ + \texttt{long long} & 8 & 8 & 8 \\ + \texttt{float} & 4 & 4 & 4 \\ + \texttt{double} & 4 & 8 & 8 \\ + \texttt{long double} & 8 & 10/12 & 16 \\ +\end{fullTable} + +\drmvspace +By default, integers in \lC\ are \texttt{signed}, to declare an unsigned integer, use \texttt{unsigned int}. +Since it is hard and annoying to remember the number of bytes that are in each data type, \texttt{C99} has introduced the extended integer types, +which can be imported from \texttt{stdint.h} and are of form \texttt{int\_t} and \texttt{uint\_t}, +where we substitute the \texttt{} with the number of bits (have to correspond to a valid type of course). + +Another notable difference of \texttt{C} compared to other languages is that \texttt{C} doesn't natively have a \texttt{boolean} type, +by convention a \texttt{short} is used to represent it, where any non-zero value means \texttt{true} and \texttt{0} means \texttt{false}. +Since boolean types are quite handy, the \texttt{!} syntax for negation turns any non-zero value of any integer type into zero and vice-versa. +\texttt{C99} has added support for a bool type via \texttt{stdbool.h}, which however is still an integer. + +Notably, \texttt{C} doesn't have a very rigid type system and lower bit-count types are implicitly cast to higher bit-count data types, i.e. +if you add a \texttt{short} and an \texttt{int}, the \texttt{short} is cast to \texttt{short} (bits 16-31 are set to $0$) and the two are added. +Explicit casting between almost all types is also supported. +Some will force a change of bit representation, but most won't (notably, when casting to and from \texttt{float}-like types, minus to \texttt{void}) + +Another important feature is that every \lC\ statement is also an expression, see above code block for example. + +The \texttt{void} type has \bi{no} value and is used for untyped pointers and declaring functions with no return value diff --git a/semester3/spca/parts/00_c/01_basics/03_operators.tex b/semester3/spca/parts/00_c/01_basics/03_operators.tex new file mode 100644 index 0000000..aae850e --- /dev/null +++ b/semester3/spca/parts/00_c/01_basics/03_operators.tex @@ -0,0 +1,43 @@ +\subsubsection{Operators} +The list of operators in \lC\ is similar to the one of \texttt{Java}, etc. +In Table \ref{tab:c-operators}, you can see an overview of the operators, sorted by precedence in descending order. +You may notice that the \verb|&| and \verb|*| operators appear twice. The higher precedence occurrence is the address operator and dereference, respectively, +and the lower precedence is \texttt{bitwise and} and \texttt{multiplication}, respectively. + +Very low precedence belongs to boolean operators \verb|&&| and \texttt{||}, as well as the ternary operator and assignment operators +\begin{table}[h!] + \begin{tables}{ll}{Operator & Associativity} + \texttt{() [] -> .} & Left-to-right \\ + \verb|! ~ ++ -- + - * & (type) sizeof| & Right-to-left \\ + \verb|* / %| & Left-to-right \\ + \verb|+ -| & Left-to-right \\ + \verb|<< >>| & Left-to-right \\ + \verb|< <= >= >| & Left-to-right \\ + \verb|== !=| & Left-to-right \\ + \verb|&| (logical and) & Left-to-right \\ + \verb|^| (logical xor) & Left-to-right \\ + \texttt{|} (logical or) & Left-to-right \\ + \verb|&&| (boolean and) & Left-to-right \\ + \texttt{||} (boolean or) & Left-to-right \\ + \texttt{? :} (ternary) & Right-to-left \\ + \verb|= += -= *= /= %= &= ^=||\verb|= <<= >>=| & Right-to-left \\ + \verb|,| & Left-to-right \\ + \end{tables} + \caption{\lC\ operators ordered in descending order by precedence} + \label{tab:c-operators} +\end{table} + +\shade{blue}{Associativity} +\begin{itemize} + \item Left-to-right: $A + B + C \mapsto (A + B) + C$ + \item Right-to-left: \texttt{A += B += C} $\mapsto$ \texttt{(A += B) += C} +\end{itemize} + +As it should be, boolean and, as well as boolean or support early termination. + +The ternary operator works as in other programming languages \verb|result = expr ? res_true : res_false;| + +As previously touched on, every statement is also an expression, i.e. the following works +\mint{c}|printf("%s", x = foo(y)); // prints output of foo(y) and x has that value| + +Pre-increment (\texttt{++i}, new value returned) and post-increment (\texttt{i++}, old value returned) are also supported by \lC. diff --git a/semester3/spca/code-examples/00_c/02_pointers.h b/semester3/spca/parts/00_c/01_basics/04_arrays.tex similarity index 100% rename from semester3/spca/code-examples/00_c/02_pointers.h rename to semester3/spca/parts/00_c/01_basics/04_arrays.tex diff --git a/semester3/spca/parts/00_c/01_basics/05_strings.tex b/semester3/spca/parts/00_c/01_basics/05_strings.tex new file mode 100644 index 0000000..e69de29 diff --git a/semester3/spca/parts/00_c/01_basics/06_pointers.tex b/semester3/spca/parts/00_c/01_basics/06_pointers.tex new file mode 100644 index 0000000..e69de29 diff --git a/semester3/spca/parts/00_c/02_preprocessor/00_intro.tex b/semester3/spca/parts/00_c/02_preprocessor/00_intro.tex new file mode 100644 index 0000000..e69de29 diff --git a/semester3/spca/spca-summary.pdf b/semester3/spca/spca-summary.pdf index 00e78cf..6834cc2 100644 Binary files a/semester3/spca/spca-summary.pdf and b/semester3/spca/spca-summary.pdf differ diff --git a/semester3/spca/spca-summary.tex b/semester3/spca/spca-summary.tex index e46a77a..f7afbab 100644 --- a/semester3/spca/spca-summary.tex +++ b/semester3/spca/spca-summary.tex @@ -7,6 +7,8 @@ \usepackage{lmodern} \setFontType{sans} +\newcommand{\lC}{\texttt{C}} + \begin{document} \startDocument \usetcolorboxes @@ -58,7 +60,13 @@ \newsection \section{The C Programming Language} \input{parts/00_c/00_intro.tex} -\input{parts/00_c/01_syntax.tex} +\input{parts/00_c/01_basics/00_intro.tex} +\input{parts/00_c/01_basics/01_control-flow.tex} +\input{parts/00_c/01_basics/02_declarations.tex} +\input{parts/00_c/01_basics/03_operators.tex} +\input{parts/00_c/01_basics/04_arrays.tex} +\input{parts/00_c/01_basics/05_strings.tex} +\input{parts/00_c/01_basics/06_pointers.tex} % ── Intro to x86 asm ────────────────────────────────────────────────