Transparency of ideal gas model selection #109

When using PC-SAFT it is somewhat unclear which ideal gas model is used (see, e.g., #68). Should the selection be more explicit? Some thoughts:

1. The default ideal gas model is nice to have because it leads to correct pressures and derivatives of pressures. However, calculating caloric properties with the default model should be discouraged. At the same time, residual caloric properties are fine.
2. Caloric properties could be hidden behind a trait similar to mass specific properties. That would not solve the problem for PC-SAFT, though, which clearly should implement that trait.
3. For PC-SAFT specifically there should probably be either one single method, or an explicit choice.

Then there is also the issue with models implemented in Python:

• Add way to specify ideal gas contribution for EoS implemented in Python #38